Triple
T31429834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dallas Cowboys 1990s Super Bowl dynasty |
E801764
|
entity |
| Predicate | keyTightEnd |
P126826
|
FINISHED |
| Object |
Jay Novacek
Jay Novacek is a former NFL tight end best known for his Pro Bowl-caliber play and clutch receiving as a core offensive weapon on the Dallas Cowboys’ championship teams of the early 1990s.
|
E1977757
|
NE FINISHED |
How this triple was built (3 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: Jay Novacek | Statement: [Dallas Cowboys 1990s Super Bowl dynasty, keyTightEnd, Jay Novacek]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Jay Novacek Triple: [Dallas Cowboys 1990s Super Bowl dynasty, keyTightEnd, Jay Novacek]
Generated description
Jay Novacek is a former NFL tight end best known for his Pro Bowl-caliber play and clutch receiving as a core offensive weapon on the Dallas Cowboys’ championship teams of the early 1990s.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyTightEnd Context triple: [Dallas Cowboys 1990s Super Bowl dynasty, keyTightEnd, Jay Novacek]
-
A.
startingTightEnd
Indicates that an entity serves as the primary tight end at the start of a game, play, season, or lineup configuration.
-
B.
isKeyPlayerFor
chosen
Indicates that an entity plays a crucial or central role in the success, functioning, or performance of another entity (such as a team, project, or organization).
-
C.
decisiveTouchdownScorer
Indicates the player who scored the touchdown that ultimately determined the outcome of the game.
-
D.
awayTeamKicker
Indicates the player who serves as the kicker for the away team in a game or match.
-
E.
keyTarget
Indicates that one entity serves as the primary focus, objective, or intended recipient of another entity’s action, function, or influence.
- F. None of above.
Provenance (6 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_69f348c475348190bf579ca858eec77c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a5f71b2c8190aade8a83f465be0c |
completed | May 3, 2026, 1:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2d9d339f188190948f6a99e4b3a3e1 |
completed | June 13, 2026, 6:10 p.m. |
| NEDg | Description generation | batch_6a2d9df2b8bc81909145216bf1bea8f6 |
completed | June 13, 2026, 6:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2d9eb095408190a454afb237e14476 |
completed | June 13, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f69fe66df08190958558d63ee623d9 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 8:56 p.m.