Triple
T16685608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Subhash Ghai |
E405454
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Ram Lakhan |
E546213
|
NE 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: Ram Lakhan | Statement: [Subhash Ghai, notableWork, Ram Lakhan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ram Lakhan Context triple: [Subhash Ghai, notableWork, Ram Lakhan]
-
A.
Ram Lakhan
chosen
Ram Lakhan is a popular 1989 Hindi masala film directed by Subhash Ghai, known for its blend of action, drama, and comedy and its ensemble cast including Anil Kapoor, Jackie Shroff, and Anupam Kher.
-
B.
HAL Ajeet
HAL Ajeet is an Indian light fighter aircraft developed by Hindustan Aeronautics Limited as an improved, license-built variant of the British Folland Gnat.
-
C.
Raj Babbar
Raj Babbar is an Indian film and television actor turned politician, known for his work in Hindi and Punjabi cinema and his long-standing association with the Indian National Congress.
-
D.
Ram Baran
Ram Baran is the given name of Ram Baran Yadav, the first president of Nepal.
-
E.
Madan Babu
Madan Babu is a computational biologist known for his influential work on gene regulation, protein networks, and systems biology.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ea550c0819085bd36c44237a61a |
completed | April 18, 2026, 12:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a43f6a08190913ca123a2377f95 |
completed | May 10, 2026, 1:38 p.m. |
Created at: April 10, 2026, 5:19 a.m.