Triple
T23176576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GM Old Look |
E579019
|
entity |
| Predicate | marketedAs |
P1395
|
FINISHED |
| Object | GM Coach |
—
|
NE NERFINISHED |
How this triple was built (2 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: GM Coach | Statement: [GM Old Look, marketedAs, GM Coach]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GM Coach Context triple: [GM Old Look, marketedAs, GM Coach]
-
A.
GM Coach Division
chosen
GM Coach Division was General Motors' bus manufacturing arm, known for producing iconic intercity coaches such as the Scenicruiser during the mid-20th century.
-
B.
Coach
Coach is a recurring character on the TV sitcom "New Girl," known as one of Jess's male roommates and a personal trainer with an intense yet often awkwardly funny personality.
-
C.
Coach
Coach is a luxury American fashion brand best known for its high-quality leather handbags, accessories, and lifestyle products.
-
D.
Coach
Coach is a supporting character in the 1986 fantasy drama film "The Boy Who Could Fly," serving as an authority figure within the school setting.
-
E.
Coach
Coach is an American television sitcom that follows the personal and professional life of a college football coach, best known for starring Craig T. Nelson.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245fd2a388190b814c0dfa15f7148 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f6b823c8190a2d39c54e48a1001 |
completed | April 29, 2026, 4:56 a.m. |
Created at: April 17, 2026, 4:04 p.m.