Triple
T21453078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Howard W. Koch |
E529266
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object |
Badge 373
Badge 373 is a 1973 American crime drama film loosely inspired by the life of New York City police detective Eddie Egan.
|
E1484662
|
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: Badge 373 | Statement: [Howard W. Koch, directed, Badge 373]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Badge 373 Context triple: [Howard W. Koch, directed, Badge 373]
-
A.
Wound Badge
The Wound Badge was a German military decoration awarded during both World Wars to soldiers who were wounded in combat.
-
B.
Expert Soldier Badge
The Expert Soldier Badge is a U.S. Army special skills badge awarded to soldiers who demonstrate a high level of proficiency in core warrior tasks and combat skills.
-
C.
Rising Sun badge
The Rising Sun badge is an iconic emblem of the Australian Army, featuring radiating sun rays and historically worn on the slouch hat by Australian soldiers.
-
D.
Garter badge
The Garter badge is an early emblem of England’s Order of the Garter, typically featuring the order’s blue garter and motto as an insignia of chivalric membership.
-
E.
EIC Badge
The EIC Badge is a U.S. military marksmanship award earned by shooters who achieve distinguished performance in Excellence-in-Competition matches.
- 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: Badge 373 Triple: [Howard W. Koch, directed, Badge 373]
Generated description
Badge 373 is a 1973 American crime drama film loosely inspired by the life of New York City police detective Eddie Egan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Badge 373 Target entity description: Badge 373 is a 1973 American crime drama film loosely inspired by the life of New York City police detective Eddie Egan.
-
A.
Wound Badge
The Wound Badge was a German military decoration awarded during both World Wars to soldiers who were wounded in combat.
-
B.
Expert Soldier Badge
The Expert Soldier Badge is a U.S. Army special skills badge awarded to soldiers who demonstrate a high level of proficiency in core warrior tasks and combat skills.
-
C.
Rising Sun badge
The Rising Sun badge is an iconic emblem of the Australian Army, featuring radiating sun rays and historically worn on the slouch hat by Australian soldiers.
-
D.
Garter badge
The Garter badge is an early emblem of England’s Order of the Garter, typically featuring the order’s blue garter and motto as an insignia of chivalric membership.
-
E.
EIC Badge
The EIC Badge is a U.S. military marksmanship award earned by shooters who achieve distinguished performance in Excellence-in-Competition matches.
- 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9d50b88819081a771596d0a2b2b |
completed | April 23, 2026, 9:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09c90cd3108190a2385924b8544a00 |
completed | May 17, 2026, 1:56 p.m. |
| NEDg | Description generation | batch_6a09c9b5f08c8190b37c854f616944a9 |
completed | May 17, 2026, 1:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09ca3c4ec48190829b1bd83b933f53 |
completed | May 17, 2026, 2:01 p.m. |
Created at: April 16, 2026, 6:07 p.m.