Triple
T21754774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Sherman |
E537007
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Zac Taylor |
—
|
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: Zac Taylor | Statement: [Sarah Sherman, spouse, Zac Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zac Taylor Context triple: [Sarah Sherman, spouse, Zac Taylor]
-
A.
Zac Taylor
chosen
Zac Taylor is an American football coach best known for leading the Cincinnati Bengals as their head coach, guiding the team to multiple playoff appearances and a Super Bowl berth.
-
B.
Jonathan Gannon
Jonathan Gannon is an American football coach best known for his defensive background and for serving as an NFL head coach.
-
C.
Marcus Freeman
Marcus Freeman is an American football coach and former linebacker who serves as the head coach of the University of Notre Dame’s storied Fighting Irish program.
-
D.
Christian Daboll
Christian Daboll is a member of the Daboll family, related to NFL head coach Brian Daboll.
-
E.
Luke Daboll
Luke Daboll is a member of the Daboll family, known primarily as a relative of NFL head coach Brian Daboll.
- 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_69e0c46eab808190b848242d63a17c47 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01d8d6d0081908e0ccfbccea58895 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 16, 2026, 6:50 p.m.