Triple
T6766638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roberta Vinci |
E154735
|
entity |
| Predicate | grandSlamSinglesBestResult |
P49845
|
FINISHED |
| Object | US Open finalist 2015 |
—
|
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: US Open finalist 2015 | Statement: [Roberta Vinci, grandSlamSinglesBestResult, US Open finalist 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grandSlamSinglesBestResult Context triple: [Roberta Vinci, grandSlamSinglesBestResult, US Open finalist 2015]
-
A.
grandSlamBestResultWimbledon
Indicates the best performance or highest round an entity has achieved at the Wimbledon tennis championships.
-
B.
grandSlamBestResultUSOpen
chosen
Indicates the best performance or highest round an entity has achieved specifically at the US Open tennis Grand Slam tournament.
-
C.
grandSlamBestResultAustralianOpen
Indicates the best performance or highest round an entity has achieved specifically at the Australian Open in Grand Slam competition.
-
D.
grandSlamBestResultFrenchOpen
Indicates the best performance or highest round an entity has achieved specifically at the French Open in Grand Slam competition.
-
E.
grandSlamSinglesTitles
Indicates the number of Grand Slam singles tennis titles an entity has won.
- 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_69c688109c1c8190added9a221292af0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2303c6881909405f0d6089dbe12 |
completed | March 27, 2026, 6:53 p.m. |
| PD | Predicate disambiguation | batch_69c6d094105881909c5806eb4afa6306 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:12 p.m.