Triple
T10416326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco Deltas |
E245523
|
entity |
| Predicate | firstCompetitiveSeason |
P26144
|
FINISHED |
| Object | 2017 |
—
|
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: 2017 | Statement: [San Francisco Deltas, firstCompetitiveSeason, 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstCompetitiveSeason Context triple: [San Francisco Deltas, firstCompetitiveSeason, 2017]
-
A.
firstKnownTournamentYear
Indicates the year in which a tournament was first known to have been held.
-
B.
firstCompetitiveDerbyYear
Indicates the year in which an entity first participated in a competitive derby event.
-
C.
firstYearPlayed
chosen
Indicates the year in which an entity (such as a person or team) first began participating in the specified activity or domain.
-
D.
firstPlayed
Indicates that one entity was the earliest or initial thing (such as a song, game, or media item) that another entity engaged with or played.
-
E.
firstKnownTournament
Indicates the earliest tournament in which the entity is known or recorded to have participated or appeared.
- 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_69d381be340c8190b05998703d42d224 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4ea108fec8190819423630888fa2b |
completed | April 7, 2026, 11:27 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb9d3648190aaabed901f22a8c0 |
completed | April 7, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:10 p.m.