Triple
T20083928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thapar |
E500073
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object | Romila Thapar |
—
|
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: Romila Thapar | Statement: [Thapar, usedBy, Romila Thapar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Romila Thapar Context triple: [Thapar, usedBy, Romila Thapar]
-
A.
Romila Thapar
chosen
Romila Thapar is a prominent Indian historian renowned for her influential scholarship on ancient India and its historiography.
-
B.
B. K. Thapar
B. K. Thapar was an Indian archaeologist noted for his significant contributions to the study of the Indus Valley Civilization and other ancient South Asian cultures.
-
C.
Karan Thapar
Karan Thapar is a prominent Indian journalist and television interviewer known for his incisive and often hard-hitting political interviews.
-
D.
Ritu Thapar
Ritu Thapar is an individual associated with the Thapar name, likely connected to the prominent Indian Thapar family or its institutions.
-
E.
Walter Doniger
Walter Doniger was an American film and television writer-director best known for his work on 1950s–1970s dramas and genre films.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655a2d2c81908a6b8fd2f209a825 |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 3:41 p.m.