Triple
T12493241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USNS Bob Hope (T-AKR-300) |
E298616
|
entity |
| Predicate | hullNumber |
P3152
|
FINISHED |
| Object |
T-AKR-300
T-AKR-300 is the hull designation of USNS Bob Hope, a large, civilian-crewed U.S. Navy vehicle cargo ship used for rapid strategic sealift operations.
|
E985863
|
NE FINISHED |
How this triple was built (4 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: T-AKR-300 | Statement: [USNS Bob Hope (T-AKR-300), hullNumber, T-AKR-300]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: T-AKR-300 Context triple: [USNS Bob Hope (T-AKR-300), hullNumber, T-AKR-300]
-
A.
KRX 300
KRX 300 is a South Korean stock market index that tracks the performance of 300 representative companies listed on the Korea Exchange.
-
B.
T-346A
T-346A is the Italian Air Force’s designation for the M-346 Master, an advanced jet trainer and light attack aircraft developed by Leonardo.
-
C.
Harukas 300
Harukas 300 is the high-rise observation deck atop Osaka’s Abeno Harukas skyscraper, offering panoramic views of the city and surrounding region.
-
D.
TR-1A
The TR-1A is a high-altitude tactical reconnaissance aircraft developed from the Lockheed U-2, optimized for battlefield surveillance and intelligence-gathering missions.
-
E.
Aka-Bo
Aka-Bo is an extinct Great Andamanese language once spoken by the Bo people of the Andaman Islands in India.
- 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: T-AKR-300 Triple: [USNS Bob Hope (T-AKR-300), hullNumber, T-AKR-300]
Generated description
T-AKR-300 is the hull designation of USNS Bob Hope, a large, civilian-crewed U.S. Navy vehicle cargo ship used for rapid strategic sealift operations.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: T-AKR-300 Target entity description: T-AKR-300 is the hull designation of USNS Bob Hope, a large, civilian-crewed U.S. Navy vehicle cargo ship used for rapid strategic sealift operations.
-
A.
KRX 300
KRX 300 is a South Korean stock market index that tracks the performance of 300 representative companies listed on the Korea Exchange.
-
B.
T-346A
T-346A is the Italian Air Force’s designation for the M-346 Master, an advanced jet trainer and light attack aircraft developed by Leonardo.
-
C.
Harukas 300
Harukas 300 is the high-rise observation deck atop Osaka’s Abeno Harukas skyscraper, offering panoramic views of the city and surrounding region.
-
D.
TR-1A
The TR-1A is a high-altitude tactical reconnaissance aircraft developed from the Lockheed U-2, optimized for battlefield surveillance and intelligence-gathering missions.
-
E.
Aka-Bo
Aka-Bo is an extinct Great Andamanese language once spoken by the Bo people of the Andaman Islands in India.
- F. None of above. chosen
Provenance (5 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_69d6ada377208190a36011199a4d8558 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94de4089c8190917a45365e641437 |
completed | April 10, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f64bab99bc8190abe6dfb7c6a7fe6f |
completed | May 2, 2026, 7:08 p.m. |
| NEDg | Description generation | batch_69f64c276d388190b58fe884466076ee |
completed | May 2, 2026, 7:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f64ce7b444819094d94bec749d7618 |
completed | May 2, 2026, 7:13 p.m. |
Created at: April 8, 2026, 9:56 p.m.