Triple
T8063387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Contai |
E188179
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object | Digha |
E415754
|
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: Digha | Statement: [Contai, hasNearbySettlement, Digha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Digha Context triple: [Contai, hasNearbySettlement, Digha]
-
A.
Digha
chosen
Digha is a popular seaside resort town in the Indian state of West Bengal, known for its long, shallow beaches along the Bay of Bengal.
-
B.
Bhabra
Bhabra is a town in the Alirajpur district of Madhya Pradesh, India, known as the birthplace of Indian revolutionary Chandra Shekhar Azad.
-
C.
Ghagra
Ghagra is a traditional long, flared skirt commonly worn by women in parts of South Asia, especially in India and Pakistan, often as part of festive or ceremonial attire.
-
D.
Dasaratha
Dasaratha is the legendary king of Ayodhya in the Hindu epic Ramayana and the father of Lord Rama.
-
E.
Dhundhari
Dhundhari is an Indo-Aryan language spoken primarily in and around Jaipur and adjoining regions of Rajasthan, India.
- 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_69ca82b42674819086840efea12478e5 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3fce95f08190b803956a20082e95 |
completed | March 31, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63da3bd08190894b2f4c977167c0 |
completed | April 1, 2026, 12:16 a.m. |
Created at: March 30, 2026, 5:26 p.m.