Triple
T20351738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harano Sur |
E496027
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Kamala Devi |
—
|
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: Kamala Devi | Statement: [Harano Sur, hasCastMember, Kamala Devi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kamala Devi Context triple: [Harano Sur, hasCastMember, Kamala Devi]
-
A.
Kamala Devi
chosen
Kamala Devi is an Indian-born actress known for her roles in American Western films and television during the 1960s.
-
B.
Arundhati Devi
Arundhati Devi was an Indian actress, filmmaker, and writer known for her work in Bengali cinema and contributions to mid-20th-century Indian film and literature.
-
C.
Arundhati Nag
Arundhati Nag is an acclaimed Indian theatre and film actress and theatre activist, best known as the founder of Bengaluru’s Ranga Shankara theatre.
-
D.
Yamini Roy
Yamini Roy is an Indian public figure known primarily as the wife of politician Varun Gandhi, a member of the Nehru–Gandhi family.
-
E.
Kamala Das
Kamala Das was a pioneering Indian poet and writer known for her bold, confessional exploration of female desire, identity, and domestic life in both English and Malayalam literature.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67850ace48190b19aff5780fef7e8 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:24 a.m.