Triple
T7660235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tollywood |
E173485
|
entity |
| Predicate | locatedInNeighborhood |
P40
|
FINISHED |
| Object | Tollygunge |
E679428
|
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: Tollygunge | Statement: [Tollywood, locatedInNeighborhood, Tollygunge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tollygunge Context triple: [Tollywood, locatedInNeighborhood, Tollygunge]
-
A.
Tollygunge
chosen
Tollygunge is a neighborhood in south Kolkata, India, best known as the historic hub of the Bengali film industry.
-
B.
Leura
Leura is a picturesque village in New South Wales, Australia, known for its heritage streetscapes, gardens, and scenic views within the Blue Mountains region.
-
C.
Merungle Hill
Merungle Hill is a rural locality within the Leeton Shire local government area in the Riverina region of New South Wales, Australia.
-
D.
Tama Hills
Tama Hills is a hilly, wooded area in western Tokyo and Kanagawa Prefecture known for its parks, residential neighborhoods, and natural landscapes on the outskirts of the Tokyo metropolitan region.
-
E.
Remete Hills
Remete Hills is a smaller hilly area that forms part of the Buda Hills region near Budapest, Hungary, known for its natural landscapes and hiking opportunities.
- 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_69c69955517c819085bc715b96d304d2 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c701a47a5c8190867e39f552c86787 |
completed | March 27, 2026, 10:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8a2206664819085c6825e63eadd6f |
completed | March 29, 2026, 3:53 a.m. |
Created at: March 27, 2026, 3:59 p.m.