Triple
T28693110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cincinnati Open |
E729338
|
entity |
| Predicate | categoryATP |
P157482
|
FINISHED |
| Object | Masters 1000 |
—
|
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: Masters 1000 | Statement: [Cincinnati Open, categoryATP, Masters 1000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: categoryATP Context triple: [Cincinnati Open, categoryATP, Masters 1000]
-
A.
ATPId
Indicates that one entity is identified as an ATP (adenosine triphosphate) molecule or carries an ATP-specific identifier in relation to another entity.
-
B.
tierRelativeToATP250
Indicates the relative competitive or organizational level of an event or entity compared to the ATP 250 tournament tier.
-
C.
tierRelativeToATP1000
chosen
Indicates the relative ranking or tier of something when compared to the ATP 1000 tournament level.
-
D.
ATPClayCourtTitlesLeader
Indicates that the subject holds the record for the most ATP clay-court singles titles among all players.
-
E.
ATPYearEndChampionshipsTitles
Indicates the number of year-end championship titles a player has won in ATP season-ending tournaments.
- 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_69f043e60b6c8190ac2cd042e77fe6e9 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 5:37 a.m.