Triple
T18912914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kumar Sangakkara |
E462650
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Kumar |
—
|
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: Kumar | Statement: [Kumar Sangakkara, givenName, Kumar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kumar Context triple: [Kumar Sangakkara, givenName, Kumar]
-
A.
Kumar
chosen
Kumar is a common Indian surname and given name used across various regions and communities in South Asia.
-
B.
Kunal Khemu
Kunal Khemu is an Indian film actor who began his career as a popular child artist in the 1990s and later gained recognition for his roles in Hindi comedies and dramas.
-
C.
Arun
Arun is a local government district and borough in West Sussex, England, named after the River Arun and encompassing coastal towns such as Bognor Regis and Littlehampton.
-
D.
Arun
Arun is a masculine given name commonly used in South Asian cultures, often associated with the sun or dawn.
-
E.
Gautam Kumar
Gautam Kumar is known as the son of legendary Indian Bengali actor Uttam Kumar.
- 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c624516c81909e6bf04707d3c71c |
completed | April 20, 2026, 6:22 a.m. |
Created at: April 10, 2026, 11:58 a.m.