Triple
T3596448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kutch |
E76150
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Kandla Port |
E72851
|
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: Kandla Port | Statement: [Kutch, contains, Kandla Port]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kandla Port Context triple: [Kutch, contains, Kandla Port]
-
A.
Kandla Port
chosen
Kandla Port is a major commercial seaport on the western coast of India, serving as one of the country’s key hubs for maritime trade and cargo handling.
-
B.
Paradip Port
Paradip Port is a major deep-water seaport on the east coast of India that serves as a key hub for maritime trade and cargo handling in the Bay of Bengal region.
-
C.
Jawaharlal Nehru Port
Jawaharlal Nehru Port is India’s largest container port and a major maritime trade hub located near Mumbai on the country’s western coast.
-
D.
Mundra Port
Mundra Port is India’s largest commercial port and a major deep-draft, all-weather cargo hub located on the Arabian Sea coast in the state of Gujarat.
-
E.
Krishnapatnam Port
Krishnapatnam Port is a major deep-water seaport on India’s eastern coast, serving as a key hub for cargo and maritime trade in the state of Andhra Pradesh.
- 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_69ad85d8042081908af94a04c410dec0 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc19b26bc8190b3cc0613a1a98361 |
completed | March 8, 2026, 6:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b403130cf081909bb90800d7dc2d6f |
completed | March 13, 2026, 12:29 p.m. |
Created at: March 8, 2026, 3:22 p.m.