Triple
T33660687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1986 NFC Championship Game |
E862342
|
entity |
| Predicate | homeTeamWideReceiver |
P52807
|
FINISHED |
| Object | Lionel Manuel |
—
|
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: Lionel Manuel | Statement: [1986 NFC Championship Game, homeTeamWideReceiver, Lionel Manuel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeTeamWideReceiver Context triple: [1986 NFC Championship Game, homeTeamWideReceiver, Lionel Manuel]
-
A.
starWideReceiver
Indicates that the entity is recognized as an outstanding or primary wide receiver, typically a leading player at that position.
-
B.
startingWideReceiver
chosen
Indicates that the specified player is designated as a starting wide receiver for a team in a game or season.
-
C.
DenverBroncosWideReceiver
Indicates that an entity is a wide receiver who plays (or played) for the Denver Broncos football team.
-
D.
touchdownReceptionLeaderForTeam
Indicates the player who has recorded the most touchdown receptions for a given team.
-
E.
oregonStateWideReceiver
Indicates a relationship where an entity serves as a wide receiver for the Oregon State football team.
- 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_69f34984c4008190bb82f33a7819da64 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f70b966860819089cf92927f47c5f1 |
completed | May 3, 2026, 8:47 a.m. |
| PD | Predicate disambiguation | batch_69f70abe43e08190b2a30930d96247c1 |
completed | May 3, 2026, 8:43 a.m. |
Created at: May 1, 2026, 1:42 a.m.