Triple
T7724250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma Long |
E175088
|
entity |
| Predicate | ITTFWorldTourGrandFinalsTitle |
P78798
|
FINISHED |
| Object | multiple men's singles titles |
—
|
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: multiple men's singles titles | Statement: [Ma Long, ITTFWorldTourGrandFinalsTitle, multiple men's singles titles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ITTFWorldTourGrandFinalsTitle Context triple: [Ma Long, ITTFWorldTourGrandFinalsTitle, multiple men's singles titles]
-
A.
otherGrandSlams
Indicates that an entity is associated with Grand Slam tournaments other than a primary or specifically referenced one.
-
B.
GrandSlams
Indicates that an entity has won or is associated with victories in major Grand Slam tournaments within a given sport.
-
C.
ATPMasters1000TitlesYear
Indicates the number of ATP Masters 1000 tournament titles a player wins in a specific calendar year.
-
D.
davisCupTitle
Indicates that the subject has won a Davis Cup tennis title, specifying a championship victory in the Davis Cup competition.
-
E.
WorldChampionshipBestResult
Indicates the best performance or highest placement an entity has ever achieved in a world championship competition.
- F. None of above. chosen
Provenance (4 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_69c6995d541c81909eaa646b1a8369a9 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7074eca4c8190bd51fd1b450729e8 |
completed | March 27, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69c7016a6cf88190b53bf4b958f0f302 |
completed | March 27, 2026, 10:15 p.m. |
| PDg | Predicate description generation | batch_69c7074cd1f081908d5e8951660e7271 |
completed | March 27, 2026, 10:40 p.m. |
Created at: March 27, 2026, 4:05 p.m.