Triple
T24971181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Court Simonne-Mathieu |
E624892
|
entity |
| Predicate | locatedAtTournamentSite |
P21366
|
FINISHED |
| Object | Roland Garros, home of the French Open |
—
|
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: Roland Garros, home of the French Open | Statement: [Court Simonne-Mathieu, locatedAtTournamentSite, Roland Garros, home of the French Open]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedAtTournamentSite Context triple: [Court Simonne-Mathieu, locatedAtTournamentSite, Roland Garros, home of the French Open]
-
A.
locationOfCompetition
chosen
Indicates the place or venue where a competition or contest takes or took place.
-
B.
holdsTournamentsIn
Indicates that an entity organizes or conducts tournaments at or within a specified location.
-
C.
arenaLocation
Indicates that an arena is located at or within a specified place or geographic location.
-
D.
sponsorLocation
Indicates that an entity acts as a sponsor for activities, events, or operations occurring at a specified location.
-
E.
locationOfSport
Indicates the place where a particular sport is played, practiced, or held.
- 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_69e2ff24512481908e9a72315b8d0354 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f66c5c13808190887180099745673b |
completed | May 2, 2026, 9:27 p.m. |
| PD | Predicate disambiguation | batch_69f66abddc448190a488852f8abdeb2c |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 18, 2026, 6:01 a.m.