Triple
T3453733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kandla Port |
E72851
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Gandhidham |
E360774
|
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: Gandhidham | Statement: [Kandla Port, nearbyCity, Gandhidham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gandhidham Context triple: [Kandla Port, nearbyCity, Gandhidham]
-
A.
Gandhidham
chosen
Gandhidham is a planned town in the Kutch district of Gujarat, India, developed primarily to resettle refugees after the Partition and serving as a key commercial hub in the region.
-
B.
Bhavnagar
Bhavnagar is a coastal city in western India known for its historic trading port, diamond cutting industry, and cultural heritage within the state of Gujarat.
-
C.
Rajkot
Rajkot is a major city in the Indian state of Gujarat, known as an important commercial and cultural center of the Saurashtra region.
-
D.
Margao
Margao is a major commercial and cultural city in South Goa, India, known for its historic Portuguese influence and role as a gateway to nearby beaches.
-
E.
Jalgaon
Jalgaon is a city in northwestern Maharashtra, India, known as a major commercial center for banana production and trade.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbaa457fc8190824ca00254e962f9 |
completed | March 8, 2026, 6:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b373a7da208190a8a9ad5ede8d4f0f |
completed | March 13, 2026, 2:17 a.m. |
Created at: March 8, 2026, 3:16 p.m.