Triple
T8881471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eric Szmanda |
E211419
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Gary Dourdan |
E210489
|
NE FINISHED |
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: Gary Dourdan | Statement: [Eric Szmanda, workedWith, Gary Dourdan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gary Dourdan Context triple: [Eric Szmanda, workedWith, Gary Dourdan]
-
A.
Gary Dourdan
chosen
Gary Dourdan is an American actor best known for playing Warrick Brown on the television series CSI: Crime Scene Investigation.
-
B.
Martin Hurson
Martin Hurson was an Irish republican and Provisional IRA member who died on hunger strike in the Maze Prison during the 1981 Irish hunger strikes.
-
C.
Andy Fickman
Andy Fickman is an American film and television director known for family-friendly comedies and energetic, commercially successful studio movies.
-
D.
Mark Roule
Mark Roule is a musician best known as a guitarist associated with the new wave band Tom Tom Club.
-
E.
Mike Gunton
Mike Gunton is a British television producer best known for his work on landmark BBC natural history documentaries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca838f9e20819096ab1f236a70381a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6168e3d881908c58cf11cf5f9a0e |
completed | April 1, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd082bbe88190a207d39f9295735e |
completed | April 3, 2026, 2:36 p.m. |
Created at: March 30, 2026, 6:53 p.m.