Triple
T7448059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kathiawar |
E171932
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Okha Port |
E528410
|
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: Okha Port | Statement: [Kathiawar, hasPort, Okha Port]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Okha Port Context triple: [Kathiawar, hasPort, Okha Port]
-
A.
Okha Port
chosen
Okha Port is a coastal port town in the Indian state of Gujarat, serving as a key maritime hub and gateway to nearby islands and trade routes in the Arabian Sea.
-
B.
Kalabahi Port
Kalabahi Port is the main seaport and maritime gateway serving the island and regency of Alor in East Nusa Tenggara, Indonesia.
-
C.
Gonoura Port
Gonoura Port is a key ferry terminal and transportation hub on Iki Island in Nagasaki Prefecture, Japan, providing passenger and vehicle connections to nearby mainland ports.
-
D.
Hagnaya Port
Hagnaya Port is a major ferry terminal in San Remigio, Cebu, serving as the primary gateway for sea travel to Bantayan Island and nearby destinations.
-
E.
Haropa Port
Haropa Port is a major French port complex and logistics hub that unites the ports of Le Havre, Rouen, and Paris along the Seine corridor.
- 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_69c68a65402881908f7869368eb746fb |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f38808fc8190b27a2b455155cb5b |
completed | March 27, 2026, 9:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c827abf3288190b146522af7fcfaa1 |
completed | March 28, 2026, 7:10 p.m. |
Created at: March 27, 2026, 3:14 p.m.