Triple
T15107117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Pipavav |
E360815
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Pipavav |
E360815
|
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: Pipavav | Statement: [Port of Pipavav, locatedIn, Pipavav]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pipavav Context triple: [Port of Pipavav, locatedIn, Pipavav]
-
A.
Pipavav
chosen
Pipavav is a coastal town in Gujarat, India, known primarily for hosting one of the country’s major private ports and associated shipbuilding and maritime industries.
-
B.
Varachha
Varachha is a major suburban area of Surat in Gujarat, India, known for its dense diamond-polishing industry and a large Patidar community.
-
C.
Marvadi
Marvadi is an alternative name for the Marwari people and their Indo-Aryan language traditionally associated with the Marwar region of Rajasthan, India.
-
D.
Dohavali
Dohavali is a poetic work in Hindi by the saint-poet Tulsidas, composed in rhyming couplets that convey devotional and moral teachings.
-
E.
Bhandirvan
Bhandirvan is a sacred forest in the Vraja region of India, revered in Hindu tradition for its association with the childhood pastimes of Lord Krishna and Radha.
- 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0058af8988190977d998f85893836 |
completed | April 15, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fedd24523081908cf12a5d6bdd634d |
completed | May 9, 2026, 7:07 a.m. |
Created at: April 10, 2026, 3:05 a.m.