Triple
T21195323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khushwant Singh |
E522310
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | All India Radio |
—
|
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: All India Radio | Statement: [Khushwant Singh, employer, All India Radio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: All India Radio Context triple: [Khushwant Singh, employer, All India Radio]
-
A.
All India Radio
chosen
All India Radio is India’s national public radio broadcaster, known for its extensive news, cultural, and music programming across the country.
-
B.
Prasar Bharati
Prasar Bharati is India’s autonomous public service broadcasting corporation, overseeing major national radio and television networks.
-
C.
Doordarshan
Doordarshan is India’s public service broadcaster and one of the country’s oldest and most widely accessible television networks.
-
D.
New Delhi Television Limited
New Delhi Television Limited (NDTV) is a prominent Indian news media company known for its influential television news channels and digital journalism platforms.
-
E.
Sansad TV
Sansad TV is an Indian parliamentary television channel that provides live coverage and analysis of proceedings from the country's legislative bodies along with related public affairs programming.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b51061388190aa03f19700d3ef04 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7333aa0fc81909b17eb6a26f389ec |
completed | April 21, 2026, 8:20 a.m. |
Created at: April 16, 2026, 3:08 p.m.