Triple
T12108324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Bridges at Toko-Ri |
E288358
|
entity |
| Predicate | aircraftCarrierDepicted |
P103332
|
FINISHED |
| Object |
USS Savo Island (fictional)
USS Savo Island is a fictional U.S. Navy escort aircraft carrier featured in the Korean War film and novel "The Bridges at Toko-Ri."
|
E963700
|
NE FINISHED |
How this triple was built (5 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: USS Savo Island (fictional) | Statement: [The Bridges at Toko-Ri, aircraftCarrierDepicted, USS Savo Island (fictional)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: USS Savo Island (fictional) Context triple: [The Bridges at Toko-Ri, aircraftCarrierDepicted, USS Savo Island (fictional)]
-
A.
USS Callaghan (DD-792)
USS Callaghan (DD-792) was a Fletcher-class destroyer of the United States Navy that served in World War II and was named in honor of Rear Admiral Daniel J. Callaghan.
-
B.
USS Guadalcanal
USS Guadalcanal was a U.S. Navy escort aircraft carrier of World War II, best known for leading the task group that captured the German submarine U-505 in 1944.
-
C.
Japanese submarine I-58
Japanese submarine I-58 was an Imperial Japanese Navy B3 type cruiser submarine best known for torpedoing and sinking the USS Indianapolis near the end of World War II.
-
D.
USS Laffey
USS Laffey was a U.S. Navy destroyer famed for its fierce World War II service, including surviving intense kamikaze attacks and earning the nickname "The Ship That Would Not Die."
-
E.
Japanese aircraft carrier Shinano
The Japanese aircraft carrier Shinano was a World War II Imperial Japanese Navy vessel, originally laid down as a Yamato-class battleship and later converted into the world's largest aircraft carrier of its time before being sunk on its maiden voyage in 1944.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: USS Savo Island (fictional) Triple: [The Bridges at Toko-Ri, aircraftCarrierDepicted, USS Savo Island (fictional)]
Generated description
USS Savo Island is a fictional U.S. Navy escort aircraft carrier featured in the Korean War film and novel "The Bridges at Toko-Ri."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: USS Savo Island (fictional) Target entity description: USS Savo Island is a fictional U.S. Navy escort aircraft carrier featured in the Korean War film and novel "The Bridges at Toko-Ri."
-
A.
USS Callaghan (DD-792)
USS Callaghan (DD-792) was a Fletcher-class destroyer of the United States Navy that served in World War II and was named in honor of Rear Admiral Daniel J. Callaghan.
-
B.
USS Guadalcanal
USS Guadalcanal was a U.S. Navy escort aircraft carrier of World War II, best known for leading the task group that captured the German submarine U-505 in 1944.
-
C.
Japanese submarine I-58
Japanese submarine I-58 was an Imperial Japanese Navy B3 type cruiser submarine best known for torpedoing and sinking the USS Indianapolis near the end of World War II.
-
D.
USS Laffey
USS Laffey was a U.S. Navy destroyer famed for its fierce World War II service, including surviving intense kamikaze attacks and earning the nickname "The Ship That Would Not Die."
-
E.
Japanese aircraft carrier Shinano
The Japanese aircraft carrier Shinano was a World War II Imperial Japanese Navy vessel, originally laid down as a Yamato-class battleship and later converted into the world's largest aircraft carrier of its time before being sunk on its maiden voyage in 1944.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftCarrierDepicted Context triple: [The Bridges at Toko-Ri, aircraftCarrierDepicted, USS Savo Island (fictional)]
-
A.
hasAircraftCarrier
Indicates that one entity possesses, operates, or includes an aircraft carrier as part of its assets or resources.
-
B.
aircraftCarrierInvolved
Indicates that an aircraft carrier participates in, is present at, or is otherwise directly involved in the specified event or situation.
-
C.
flagshipCarrierOf
Indicates that one entity serves as the primary or most prominent carrier (such as an airline or telecommunications provider) representing or associated with another entity, typically a country, brand, or organization.
-
D.
fleetFlagshipOf
Indicates that one entity serves as the primary or leading flagship of a particular fleet.
-
E.
squadronFlagshipOf
Indicates that one entity serves as the primary or lead flagship vessel of a particular squadron.
- F. None of above. chosen
Provenance (7 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9164ada5081908676bd9e5947268a |
completed | April 10, 2026, 3:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f67b3f2c8190bcb2120781f91220 |
completed | May 2, 2026, 1:04 p.m. |
| NEDg | Description generation | batch_69f5fde880f4819094b2170bf4e82138 |
completed | May 2, 2026, 1:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f5ffc563a08190b95db768df475a3a |
completed | May 2, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69d9150497408190921334d21503375a |
completed | April 10, 2026, 3:19 p.m. |
| PDg | Predicate description generation | batch_69d916481a008190ae66677b9e6dd961 |
completed | April 10, 2026, 3:24 p.m. |
Created at: April 8, 2026, 9:49 p.m.