Triple
T3580353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guillermo Coria |
E75783
|
entity |
| Predicate | juniorGrandSlamTitles |
P44418
|
FINISHED |
| Object | boys' singles champion at Roland Garros |
—
|
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: boys' singles champion at Roland Garros | Statement: [Guillermo Coria, juniorGrandSlamTitles, boys' singles champion at Roland Garros]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: juniorGrandSlamTitles Context triple: [Guillermo Coria, juniorGrandSlamTitles, boys' singles champion at Roland Garros]
-
A.
grandSlamSinglesTitles
Indicates the number of Grand Slam singles tennis titles an entity has won.
-
B.
otherGrandSlams
Indicates that an entity is associated with Grand Slam tournaments other than a primary or specifically referenced one.
-
C.
GrandSlams
Indicates that an entity has won or is associated with victories in major Grand Slam tournaments within a given sport.
-
D.
hasWonGrandSlamTitleType
chosen
Indicates that an entity has won at least one Grand Slam title of a specified type (e.g., singles, doubles, mixed).
-
E.
grandSlamOrder
Indicates that one event or achievement in a sequence is a grand slam and specifies its relative order or position among other such events.
- 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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0ffecdc8190bf01c8ba90e3733e |
completed | March 8, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69adb83810c481909c645c08b978edc1 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:21 p.m.