Triple
T20279465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sloane Stephens |
E503099
|
entity |
| Predicate | reachedGrandSlamFinal |
P119091
|
FINISHED |
| Object | 2018 French Open women's singles |
—
|
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: 2018 French Open women's singles | Statement: [Sloane Stephens, reachedGrandSlamFinal, 2018 French Open women's singles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reachedGrandSlamFinal Context triple: [Sloane Stephens, reachedGrandSlamFinal, 2018 French Open women's singles]
-
A.
grandSlamFinalistInSingles
chosen
Indicates that a person has reached the final round of a Grand Slam tennis tournament in singles competition.
-
B.
achievedCareerGrandSlam
Indicates that an individual has won all major titles or championships required within a particular career-defining series or circuit at least once.
-
C.
reachedSemiFinalOf
Indicates that an entity progressed far enough in a competition or tournament to participate in its semi-final round.
-
D.
helpedWinGrandSlamsWith
Indicates that one entity significantly contributed to another entity’s victories in Grand Slam tournaments.
-
E.
yearOfGrandSlam
Indicates the specific year in which a particular Grand Slam event or achievement took place.
- 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_69e0b4b0e79c8190bd61f22ef1329fa8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6768ddfd0819098b2cc7fed0f4fe2 |
completed | April 20, 2026, 6:55 p.m. |
| PD | Predicate disambiguation | batch_69e55b1e5e1c8190ba8a5544b1db9e1d |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 16, 2026, 10:36 a.m.