Triple
T13902745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Talk Art |
E334267
|
entity |
| Predicate | hostProfessionOfHost1 |
P35550
|
FINISHED |
| Object | actor |
—
|
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: actor | Statement: [Talk Art, hostProfessionOfHost1, actor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostProfessionOfHost1 Context triple: [Talk Art, hostProfessionOfHost1, actor]
-
A.
hostsIndustry
Indicates that one entity provides the venue, infrastructure, or environment in which a particular industry operates or is based.
-
B.
memberProfession
chosen
Indicates that a member or individual holds or practices a particular profession or occupation.
-
C.
sponsorOccupation
Indicates that one entity serves as the occupation or professional role of a sponsor associated with another entity.
-
D.
hostStar
Indicates that one celestial object serves as the primary star around which another object, such as a planet or system, is associated or orbits.
-
E.
coHostOf
Indicates a relationship where two or more entities jointly host the same event, program, or activity together.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de25d9c7a48190ad8fb0ca676f4f7b |
completed | April 14, 2026, 11:32 a.m. |
| PD | Predicate disambiguation | batch_69dd464b1ab48190ae50bfc902bf6ef7 |
completed | April 13, 2026, 7:38 p.m. |
Created at: April 9, 2026, 10:16 p.m.