Triple
T23846453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sonu Nigam |
E592033
|
entity |
| Predicate | hasPerformedForIndustry |
P17879
|
FINISHED |
| Object | Bollywood |
—
|
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: Bollywood | Statement: [Sonu Nigam, hasPerformedForIndustry, Bollywood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPerformedForIndustry Context triple: [Sonu Nigam, hasPerformedForIndustry, Bollywood]
-
A.
hasIndustryProgram
Indicates that an entity offers, participates in, or is associated with a structured program involving collaboration or engagement with industry organizations or sectors.
-
B.
hasSettingInIndustry
Indicates that something (such as a work, event, or scenario) takes place within or is situated in a particular industry context.
-
C.
hasHistoricIndustry
Indicates that an entity has been associated with a notable or historically significant industry or industrial activity in the past.
-
D.
hasIndustrySection
Indicates that an entity belongs to, is categorized under, or is associated with a particular industry section.
-
E.
hasWorkedIn
chosen
Indicates that a person has been employed or has performed work within a particular organization, location, or domain for some period of time.
- 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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c88c9bbc81909204120279e6d980 |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:10 p.m.