Triple
T27102618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taran Noah Smith |
E686480
|
entity |
| Predicate | childPerformerOn |
P67683
|
FINISHED |
| Object | Home Improvement |
—
|
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: Home Improvement | Statement: [Taran Noah Smith, childPerformerOn, Home Improvement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: childPerformerOn Context triple: [Taran Noah Smith, childPerformerOn, Home Improvement]
-
A.
childPerformer
chosen
Indicates a relationship where the subject is a performer who is a child, typically under a certain age, participating in a performance or production.
-
B.
childIs
Indicates that one entity is the child (offspring or subordinate descendant) of another entity.
-
C.
childIn
Indicates that one entity is the offspring or direct descendant of another entity.
-
D.
childRepresents
Indicates that a child entity serves as a representation, proxy, or stand-in for another entity in some context or structure.
-
E.
performerOn
Indicates that an entity serves as the performer or executing agent of an action, event, or work associated with another entity.
- 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_69ef1489f8b481908e24a1985982bd26 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62d53ad58819080c5227c7a729d15 |
completed | May 2, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69f62c15952881908a5ea0c25904afec |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 8:48 a.m.