Triple
T3701668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Ditka |
E80791
|
entity |
| Predicate | roleWithDallasCowboys |
P13665
|
FINISHED |
| Object | assistant coach |
—
|
LITERAL 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: assistant coach | Statement: [Mike Ditka, roleWithDallasCowboys, assistant coach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleWithDallasCowboys Context triple: [Mike Ditka, roleWithDallasCowboys, assistant coach]
-
A.
roleAtTampaBayBuccaneers
Indicates that an entity holds or held a specific role or position within the Tampa Bay Buccaneers organization.
-
B.
roleAtNewEnglandPatriots
Indicates the specific role, position, or capacity an entity holds within the New England Patriots organization.
-
C.
roleAtSportsTeam
chosen
Indicates the specific position or function an individual holds within a sports team.
-
D.
NFLTeam
Indicates a relationship where an entity is identified as a professional American football team that competes in the National Football League.
-
E.
roleInFranchiseHistory
Indicates the specific function, position, or contribution an entity has within the historical development or timeline of a franchise.
- F. None of above.
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_69ad8b1793888190a5f70e4b21dc05a1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adc547c1848190a1ece46c59b7c43d |
completed | March 8, 2026, 6:51 p.m. |
| PD | Predicate disambiguation | batch_69adb84eeca48190bb4de637e9f0e27a |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:33 p.m.