Triple
T23900016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dallas Cowboys Doomsday Defense |
E601014
|
entity |
| Predicate | Doomsday IKeyPlayer |
P126826
|
FINISHED |
| Object | Bob Lilly |
—
|
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: Bob Lilly | Statement: [Dallas Cowboys Doomsday Defense, Doomsday IKeyPlayer, Bob Lilly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Doomsday IKeyPlayer Context triple: [Dallas Cowboys Doomsday Defense, Doomsday IKeyPlayer, Bob Lilly]
-
A.
Invoker
Indicates that one entity initiates or triggers an action, process, or event involving another entity.
-
B.
commanderDeath
Indicates that an entity dies while serving in the role of a commander or as the leader in a command position.
-
C.
bossCharacter
Indicates that one character serves as the primary, often more powerful, opponent or leader that others must confront or overcome.
-
D.
deathEmpire
Indicates a relationship where an empire causes, is associated with, or is characterized by widespread death or destruction.
-
E.
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).
- 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_69e295341ac0819080647f2908af793c |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cdddca088190b6c26df984a143ad |
completed | April 29, 2026, 9:22 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:26 p.m.