Triple
T16328510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montpellier Hérault Rugby |
E396485
|
entity |
| Predicate | top14Titles |
P79051
|
FINISHED |
| Object | 1 |
—
|
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: 1 | Statement: [Montpellier Hérault Rugby, top14Titles, 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: top14Titles Context triple: [Montpellier Hérault Rugby, top14Titles, 1]
-
A.
mostTitlesTeamTitles
Indicates that the referenced team holds the highest number of titles compared to all other teams in the specified context.
-
B.
numberOfLeagueTitles
Indicates the total count of league championship titles that an entity has won.
-
C.
countryTopDivisionTitles
chosen
Indicates the number of top-tier national league titles an entity has won in a given country.
-
D.
countryWithMostTitles
Indicates the country that holds the highest number of titles (e.g., championships or awards) within a specified competition or context.
-
E.
runnerUpMostTitles
Indicates that an entity holds the record for having the highest number of runner-up finishes or second-place titles in a given competition or context.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4ddc5608190b24fe2e871691470 |
completed | April 17, 2026, 11:40 p.m. |
| PD | Predicate disambiguation | batch_69e226eba9b48190af6e80d3d1c2aed3 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:07 a.m.