Triple
T183097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple Cup |
E3919
|
entity |
| Predicate | playedAfter |
P6586
|
FINISHED |
| Object | National League regular season |
—
|
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: National League regular season | Statement: [Temple Cup, playedAfter, National League regular season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playedAfter Context triple: [Temple Cup, playedAfter, National League regular season]
-
A.
playedKeyRoleIn
Indicates that an entity had a major, influential, or decisive impact on the occurrence, outcome, or success of another entity or event.
-
B.
playedFor
Indicates that one entity has been a member of or participated as a player for a particular team, organization, or group.
-
C.
introducedTo
Indicates that one entity caused or facilitated a first meeting or formal presentation between another entity and a third party.
-
D.
hasNotableRecordingBy
Indicates that an entity (such as a work or composition) has a well-known or significant recording created or performed by a specified agent (such as an artist, ensemble, or label).
-
E.
performed
Indicates that an entity carried out, executed, or conducted a specific action, task, or activity.
- F. None of above. chosen
Provenance (4 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_69a25497e2f08190a040f8c6e1842643 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a2592516748190a85ae58eec191f14 |
completed | Feb. 28, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69a2566dfc388190988b1b42d5daaafe |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a257e763d081908c54ad57d8d3060d |
completed | Feb. 28, 2026, 2:50 a.m. |
Created at: Feb. 28, 2026, 2:40 a.m.