Triple
T9279345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kelly Kapoor |
E223029
|
entity |
| Predicate | lastRegularAppearanceSeason |
P57359
|
FINISHED |
| Object | Season 8 |
—
|
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: Season 8 | Statement: [Kelly Kapoor, lastRegularAppearanceSeason, Season 8]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastRegularAppearanceSeason Context triple: [Kelly Kapoor, lastRegularAppearanceSeason, Season 8]
-
A.
lastWorksSeason
chosen
Indicates the season in which an entity (such as a person or organization) last performed work or was active in a particular role or context.
-
B.
lastCompletedSeason
Indicates the most recent season of an ongoing or episodic series that has been fully finished or concluded.
-
C.
seasonAppearance
Indicates that an entity appears in, or is present during, a particular season within a series or sequence.
-
D.
lastGameSeason
Indicates that one entity is the final or most recent game season associated with another entity.
-
E.
lastChampionshipGameSeason
Indicates the season in which an entity most recently participated in a championship game.
- 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_69ca842123588190b3f2e1a69037d141 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd07cc79508190954defbef0d82a64 |
completed | April 1, 2026, 11:55 a.m. |
| PD | Predicate disambiguation | batch_69cc7a576ec88190bbb787eb82e2e539 |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:34 p.m.