Triple
T20844869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vector |
E513193
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Pierre Coffin |
—
|
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: Pierre Coffin | Statement: [Vector, createdBy, Pierre Coffin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pierre Coffin Context triple: [Vector, createdBy, Pierre Coffin]
-
A.
Pierre Coffin
chosen
Pierre Coffin is a French animator and film director best known as the co-creator of the Minions and the voice behind their characters in the Despicable Me franchise.
-
B.
Mike Jost
Mike Jost is a musician best known as the drummer for the punk rock band Helmet.
-
C.
Michel Zitt
Michel Zitt is a prominent French scholar in scientometrics and research evaluation, recognized internationally for his influential contributions to the quantitative study of science and technology.
-
D.
Denis Douyon
Denis Douyon is a researcher known for his scholarly work on the Dogon languages of Mali.
-
E.
Gary Dourdan
Gary Dourdan is an American actor best known for playing Warrick Brown on the television series CSI: Crime Scene Investigation.
- 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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c34deef88190992b959b83bc59b1 |
completed | April 21, 2026, 12:22 a.m. |
Created at: April 16, 2026, 12:43 p.m.