Triple
T14809409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Flack |
E348132
|
entity |
| Predicate | worksWith |
P398
|
FINISHED |
| Object | Mac Taylor |
E348128
|
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: Mac Taylor | Statement: [Don Flack, worksWith, Mac Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mac Taylor Context triple: [Don Flack, worksWith, Mac Taylor]
-
A.
Mac Taylor
chosen
Mac Taylor is the dedicated and methodical head of the New York crime lab in the television series CSI: NY, known for his strong moral code and forensic expertise.
-
B.
Brian Taylor
Brian Taylor is known as the former long-term partner of acclaimed British actor Sir Ian McKellen.
-
C.
Brian Taylor
Brian Taylor is an American filmmaker best known for co-directing the hyper-kinetic action films "Crank" and "Crank: High Voltage."
-
D.
Mike Taylor
Mike Taylor is a songwriter best known for co-writing John Denver’s classic folk song "Rocky Mountain High."
-
E.
Mike Taylor
Mike Taylor is a film editor known for his work on the acclaimed British gangster film "The Long Good Friday."
- 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_69d822ea8b7c819097dfadf3d45545e6 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decf35a5e081909321193ef37099d1 |
completed | April 14, 2026, 11:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe72a4f71881909c3c1cc09fe89a60 |
completed | May 8, 2026, 11:32 p.m. |
Created at: April 10, 2026, 1:45 a.m.