Triple
T6145303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indiana Fever |
E137059
|
entity |
| Predicate | wonConferenceTitleInSeason |
P5860
|
FINISHED |
| Object | 2009 |
—
|
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: 2009 | Statement: [Indiana Fever, wonConferenceTitleInSeason, 2009]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonConferenceTitleInSeason Context triple: [Indiana Fever, wonConferenceTitleInSeason, 2009]
-
A.
wonConferenceTitle
chosen
Indicates that an entity secured the championship or first-place title in a conference-level competition or league.
-
B.
wonChampionshipInSeason
Indicates that an entity secured a championship title during a specified season.
-
C.
wonLeagueTitle
Indicates that a team or individual finished a competition as champions, securing the league title for that season or tournament.
-
D.
wonDivisionTitle
Indicates that an entity secured first place in its competitive division, earning the division championship title.
-
E.
tournamentWinsInSeason
Indicates that one entity (typically a team or player) has achieved a specified number of tournament victories during a particular season.
- 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_69c008a2c6308190a56519b22d55d083 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05cdd2dc0819080a4adf0cead3603 |
completed | March 22, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69c055f39e0881909ae56444b1b48929 |
completed | March 22, 2026, 8:49 p.m. |
Created at: March 22, 2026, 4:16 p.m.