Triple
T26175707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2002 FIFA World Cup third place match against South Korea |
E654533
|
entity |
| Predicate | teamCoachOfSouthKorea |
P2169
|
FINISHED |
| Object | Guus Hiddink |
—
|
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: Guus Hiddink | Statement: [2002 FIFA World Cup third place match against South Korea, teamCoachOfSouthKorea, Guus Hiddink]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamCoachOfSouthKorea Context triple: [2002 FIFA World Cup third place match against South Korea, teamCoachOfSouthKorea, Guus Hiddink]
-
A.
coachOf
chosen
Indicates that one entity serves as the coach (trainer or manager) of another entity, typically a person or team.
-
B.
headCoachOfHomeTeam
Indicates that a person serves as the head coach of the designated home team in a sporting event or competition.
-
C.
headCoachFullName
Indicates the full personal name of the individual who serves as head coach for a given team or organization.
-
D.
headCoachTeam
Indicates that a person serves as the head coach of a particular team.
-
E.
coachedTeamInCountry
Indicates that a person served as a coach for a particular team while that team was based in or associated with a specified country.
- 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_69ee5b45873c81909499203612d05d07 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f63182f1408190bddc1214fcbd6145 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 26, 2026, 8:37 p.m.