Triple
T21110604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kulbhushan Kharbanda |
E520160
|
entity |
| Predicate | hasActedIn |
P15620
|
FINISHED |
| Object | Arth |
—
|
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: Arth | Statement: [Kulbhushan Kharbanda, hasActedIn, Arth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arth Context triple: [Kulbhushan Kharbanda, hasActedIn, Arth]
-
A.
Arth
chosen
Arth is a critically acclaimed 1982 Indian Hindi-language drama film directed by Mahesh Bhatt, known for its realistic portrayal of marital discord and strong female characters.
-
B.
Arth
Arth is a Swiss lakeside municipality in the canton of Schwyz, situated on the shores of Lake Zug and known for its scenic Alpine surroundings.
-
C.
Arthog
Arthog is a small village in Gwynedd, Wales, situated near the Mawddach Estuary and known for its scenic coastal and mountain surroundings.
-
D.
Ard
Ard is the Middle Persian form of the Avestan name Asha, a key Zoroastrian concept signifying truth, order, and righteousness.
-
E.
Aru
Aru is a group of closely related Austronesian languages spoken primarily in the Aru Islands of eastern Indonesia.
- 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_69e0b509a318819092fbbcb21d1fe603 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72101f7308190beb202a052ff04d2 |
completed | April 21, 2026, 7:02 a.m. |
Created at: April 16, 2026, 2:54 p.m.