Triple
T22633255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nathalie Péchalat |
E558609
|
entity |
| Predicate | formerCompetitiveStatus |
P87635
|
FINISHED |
| Object | retired |
—
|
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: retired | Statement: [Nathalie Péchalat, formerCompetitiveStatus, retired]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerCompetitiveStatus Context triple: [Nathalie Péchalat, formerCompetitiveStatus, retired]
-
A.
formerCompetitionLevel
Indicates that an entity previously participated at a specified level of competition, but no longer does so.
-
B.
formerPlayerType
Indicates that an entity previously had a specific player role or classification but no longer holds that status.
-
C.
formerAthlete
chosen
Indicates that a person previously had the role or status of an athlete but no longer does.
-
D.
competitiveStatus
Indicates the nature or level of competition that exists between entities, such as whether they are rivals, collaborators, or non-competitors.
-
E.
formerSport
Indicates that an entity previously played or participated in a particular sport but no longer does so.
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1700ab4308190a16b0a1b2a0210fd |
completed | April 29, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_69ee62855558819080da946c7b35a160 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 3:03 p.m.