Triple

T18747247
Position Surface form Disambiguated ID Type / Status
Subject Hadramawt E458434 entity
Predicate hasPort P35 FINISHED
Object Port of Mukalla 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: Port of Mukalla | Statement: [Hadramawt, hasPort, Port of Mukalla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Port of Mukalla
Context triple: [Hadramawt, hasPort, Port of Mukalla]
  • A. Port of Mukalla chosen
    The Port of Mukalla is a key maritime gateway and commercial seaport on Yemen’s southern coast, serving the Hadhramaut region on the Arabian Sea.
  • B. Port of Al Hudaydah
    The Port of Al Hudaydah is a major Red Sea seaport in western Yemen that serves as a key hub for the country’s maritime trade and humanitarian aid shipments.
  • C. Port of Muscat
    The Port of Muscat is a historic harbor in Oman’s capital that has long served as a key maritime gateway for regional trade and cultural exchange along the Arabian Sea.
  • D. Adabiya Port
    Adabiya Port is a commercial seaport on Egypt’s Red Sea coast that serves as a key hub for handling general cargo and bulk goods.
  • E. Farasan Port
    Farasan Port is a Saudi Arabian maritime facility serving the Farasan Islands, supporting regional transport, trade, and access to the Red Sea.
  • 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_69e576936cf08190b3c0d2f4e8a616fc completed April 20, 2026, 12:42 a.m.
Created at: April 10, 2026, 11:51 a.m.