Triple
T22273799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Five Rifles |
E550548
|
entity |
| Predicate | featuresActor |
P15562
|
FINISHED |
| Object | Ambika Johar |
—
|
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: Ambika Johar | Statement: [Five Rifles, featuresActor, Ambika Johar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ambika Johar Context triple: [Five Rifles, featuresActor, Ambika Johar]
-
A.
Ambika Johar
chosen
Ambika Johar is an actress best known for her role in the 1974 Hindi war drama film "Five Rifles."
-
B.
Vicky Ahuja
Vicky Ahuja is an Indian actor known for his supporting roles in Hindi films and web series, including the thriller "A Thursday."
-
C.
Zeenat Lakhani
Zeenat Lakhani is an Indian screenwriter best known for co-writing the acclaimed Hindi film "Hindi Medium."
-
D.
Meghna Kapoor
Meghna Kapoor is known as the wife of Indian actor and filmmaker Rajat Kapoor.
-
E.
Neha Dhupia
Neha Dhupia is an Indian actress and former Miss India who has appeared in numerous Bollywood films and television shows.
- 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_69e11e43d8208190aff4f9cf7f2c2a8a |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f14ea547e4819098baf88f3c605242 |
completed | April 29, 2026, 12:19 a.m. |
Created at: April 16, 2026, 8:40 p.m.