Triple
T36841734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | XX |
E910425
|
entity |
| Predicate | hasAFCChampionshipGame |
P56878
|
FINISHED |
| Object | 1985 AFC Championship Game |
—
|
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: 1985 AFC Championship Game | Statement: [XX, hasAFCChampionshipGame, 1985 AFC Championship Game]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAFCChampionshipGame Context triple: [XX, hasAFCChampionshipGame, 1985 AFC Championship Game]
-
A.
isAFCChampion
Indicates that an entity has won the championship title of the American Football Conference (AFC) in a given season.
-
B.
hasFootballChampionshipGame
chosen
Indicates that an entity hosts, organizes, or is associated with a football championship game.
-
C.
hasChampionshipGames
Indicates that an entity includes, hosts, or is associated with one or more championship-level games or matches.
-
D.
previousAFCChampionshipGame
Indicates that one AFC Championship Game immediately precedes another in chronological order.
-
E.
playsChampionshipGame
Indicates that an entity participates as a competitor in a championship-level game or match.
- 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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.