Triple
T3777188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kris Humphries |
E83334
|
entity |
| Predicate | formerSport |
P50868
|
FINISHED |
| Object | swimming |
—
|
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: swimming | Statement: [Kris Humphries, formerSport, swimming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerSport Context triple: [Kris Humphries, formerSport, swimming]
-
A.
formerLeague
Indicates that an entity previously belonged to or participated in a particular league but is no longer a member.
-
B.
sportsCareer
Indicates a relationship where an entity’s professional involvement, roles, or achievements in sports are associated with a particular sport, team, period, or competitive level.
-
C.
primarySport
Indicates the main sport with which an entity (such as a person, team, or organization) is most closely associated or primarily involved.
-
D.
originalSport
Indicates that one sport is the initial or primary sport associated with an entity, often before any change, adaptation, or transition to another sport.
-
E.
knownForSports
Indicates that an entity is recognized or notable for its involvement, achievement, or association with sports.
- 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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc5d3dbc8190b6ab118a56acd5a3 |
completed | March 8, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69adc050cc5c81909d9855f866f3c26d |
completed | March 8, 2026, 6:30 p.m. |
| PDg | Predicate description generation | batch_69adc0fe3e3c8190bd886c7745c172a0 |
completed | March 8, 2026, 6:33 p.m. |
Created at: March 8, 2026, 3:36 p.m.