Triple
T18748438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cutch State |
E458462
|
entity |
| Predicate | notablePort |
P6498
|
FINISHED |
| Object | Mandvi |
—
|
NE NERFINISHED |
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: Mandvi | Statement: [Cutch State, notablePort, Mandvi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mandvi Context triple: [Cutch State, notablePort, Mandvi]
-
A.
Mandvi
chosen
Mandvi is a historic coastal town in Gujarat, India, known for its shipbuilding heritage, beaches, and trading history within the Kutch region.
-
B.
Vohra
Vohra is an Indian surname commonly associated with Punjabi and North Indian communities, including notable figures in politics, business, and public life.
-
C.
Vengurla
Vengurla is a coastal town in Maharashtra, India, known for its scenic beaches, historic forts, and cashew plantations.
-
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.
Mandwara
Mandwara is an alternative name for the Mandara language, an Afro-Asiatic language spoken primarily in parts of Cameroon and Nigeria.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579e9903c81908180c46012bd0948 |
completed | April 20, 2026, 12:57 a.m. |
Created at: April 10, 2026, 11:51 a.m.