Triple
T3868660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Type 93 Long Lance torpedo |
E91922
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object |
Long Lance
Long Lance is the Allied nickname for Japan’s Type 93 torpedo, a highly advanced and powerful World War II naval weapon renowned for its exceptional range and destructive capability.
|
E394603
|
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: Long Lance | Statement: [Type 93 Long Lance torpedo, nickname, Long Lance]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Long Lance Context triple: [Type 93 Long Lance torpedo, nickname, Long Lance]
-
A.
Paris Gun
The Paris Gun was a long-range German artillery piece used in World War I to bombard Paris from unprecedented distances.
-
B.
Haynrode
Haynrode is a small village in the German state of Thuringia.
-
C.
Shrapnel
Shrapnel is a military science fiction comic and graphic novel series set in a future interplanetary war where a former officer leads a rebellion against a powerful solar alliance.
-
D.
Stinger
Stinger is the anthropomorphic green hornet mascot of the NHL’s Columbus Blue Jackets, known for his energetic presence at games and team events.
-
E.
Scud
Scud is a supporting character in the film "Blade II," serving as a young, tech-savvy ally who assists Blade with weapons and equipment.
- 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: Long Lance Triple: [Type 93 Long Lance torpedo, nickname, Long Lance]
Generated description
Long Lance is the Allied nickname for Japan’s Type 93 torpedo, a highly advanced and powerful World War II naval weapon renowned for its exceptional range and destructive capability.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Long Lance Target entity description: Long Lance is the Allied nickname for Japan’s Type 93 torpedo, a highly advanced and powerful World War II naval weapon renowned for its exceptional range and destructive capability.
-
A.
Paris Gun
The Paris Gun was a long-range German artillery piece used in World War I to bombard Paris from unprecedented distances.
-
B.
Haynrode
Haynrode is a small village in the German state of Thuringia.
-
C.
Shrapnel
Shrapnel is a military science fiction comic and graphic novel series set in a future interplanetary war where a former officer leads a rebellion against a powerful solar alliance.
-
D.
Stinger
Stinger is the anthropomorphic green hornet mascot of the NHL’s Columbus Blue Jackets, known for his energetic presence at games and team events.
-
E.
Scud
Scud is a supporting character in the film "Blade II," serving as a young, tech-savvy ally who assists Blade with weapons and equipment.
- 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_69aed9645f348190a9868e7cef56ab7e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec3dfb3c8190a0a07070f0d76bf6 |
completed | March 9, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b512440b8c8190ae2048bfcdd565ec |
completed | March 14, 2026, 7:46 a.m. |
| NEDg | Description generation | batch_69b512f4041081908eb32ae059681afa |
completed | March 14, 2026, 7:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5137200a08190bd2a78398e03803e |
completed | March 14, 2026, 7:51 a.m. |
Created at: March 9, 2026, 3:20 p.m.