Triple
T15920662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shankar |
E386083
|
entity |
| Predicate | notableBearer |
P458
|
FINISHED |
| Object | Anoushka Shankar |
E801378
|
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: Anoushka Shankar | Statement: [Shankar, notableBearer, Anoushka Shankar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anoushka Shankar Context triple: [Shankar, notableBearer, Anoushka Shankar]
-
A.
Anoushka Shankar
chosen
Anoushka Shankar is a renowned British-Indian sitar player and composer celebrated for her innovative blend of Indian classical music with global contemporary styles.
-
B.
Anoushka Ajith
Anoushka Ajith is the daughter of prominent Indian Tamil film actor Ajith Kumar and his wife Shalini.
-
C.
Swati Pandit
Swati Pandit is an Indian-American figure best known as the wife of former Citigroup CEO Vikram Pandit.
-
D.
Shubha Yagnik
Shubha Yagnik is the daughter of renowned Indian playback singer Alka Yagnik.
-
E.
Shankar Mahadevan
Shankar Mahadevan is an acclaimed Indian playback singer and composer known for his work across multiple languages and as a member of the Shankar–Ehsaan–Loy trio in film music.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156818cbc819086c956475ad23825 |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb5a96e508190a64c2be6dc506e86 |
completed | May 9, 2026, 10:31 p.m. |
Created at: April 10, 2026, 4:52 a.m.