Triple
T36289260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiji women’s national rugby sevens team |
E893176
|
entity |
| Predicate | worldCupSevens2018HostCity |
P197892
|
FINISHED |
| Object | San Francisco |
—
|
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: San Francisco | Statement: [Fiji women’s national rugby sevens team, worldCupSevens2018HostCity, San Francisco]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worldCupSevens2018HostCity Context triple: [Fiji women’s national rugby sevens team, worldCupSevens2018HostCity, San Francisco]
-
A.
2018HostCountry
Indicates that a country served as the host nation for a particular event in the year 2018.
-
B.
countryOfFinalVenue
Indicates the country in which the final event or venue associated with something (e.g., a competition or series) is located.
-
C.
worldCupHost
Indicates that one entity serves as the host country or location for a particular FIFA World Cup tournament.
-
D.
worldCupSevens2018Opponent
Indicates that one entity was the opposing team faced by the other entity in a match during the 2018 Rugby World Cup Sevens.
-
E.
2021EditionHostCountry
Indicates the country that served as the host for the 2021 edition of a particular event or competition.
- 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_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
| PDg | Predicate description generation | batch_69feb5e50a7481908d6bff55bd85e06d |
completed | May 9, 2026, 4:19 a.m. |
Created at: May 3, 2026, 4:09 p.m.