Triple
T19955222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hungary at the Olympic Games |
E479663
|
entity |
| Predicate | strongSport |
P1080
|
FINISHED |
| Object | fencing |
—
|
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: fencing | Statement: [Hungary at the Olympic Games, strongSport, fencing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strongSport Context triple: [Hungary at the Olympic Games, strongSport, fencing]
-
A.
multiSport
Indicates that an entity participates in, is associated with, or is designed for more than one sport.
-
B.
sportGender
Indicates that a sport or sporting event is associated with a particular gender category (e.g., men's, women's, mixed).
-
C.
sportsAndRecreation
Indicates a relationship where an entity is associated with, involved in, or designated for sports or recreational activities.
-
D.
primarySport
chosen
Indicates the main sport with which an entity (such as a person, team, or organization) is most closely associated or primarily involved.
-
E.
primarySports
Indicates that a particular sport is the main or most important sport associated with an entity (such as a person, team, or organization).
- 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65aefd9488190b8cdfa8543db8d31 |
completed | April 20, 2026, 4:57 p.m. |
| PD | Predicate disambiguation | batch_69e537f47c508190853c4e009c6b5566 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:54 p.m.