Triple

T22357192
Position Surface form Disambiguated ID Type / Status
Subject Orca Inlet E552684 entity
Predicate hasPort P35 FINISHED
Object Cordova Harbor 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: Cordova Harbor | Statement: [Orca Inlet, hasPort, Cordova Harbor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cordova Harbor
Context triple: [Orca Inlet, hasPort, Cordova Harbor]
  • A. Cordova Harbor chosen
    Cordova Harbor is a small commercial and fishing port serving the coastal community of Cordova in Prince William Sound, Alaska.
  • B. Cid Harbour
    Cid Harbour is a sheltered anchorage and scenic bay within Australia’s Whitsunday Islands, popular with yachties and visitors for its calm waters and natural surroundings.
  • C. New Harbour
    New Harbour is the former name of Keppel Harbour, a historically significant maritime port area in Singapore.
  • D. Coral Harbour
    Coral Harbour is a small Inuit community located on Southampton Island in Nunavut, Canada, known for its remote Arctic setting and traditional subsistence lifestyle.
  • E. Crooked Harbour
    Crooked Harbour is a sheltered inlet on the northeastern coast of Hong Kong, known for its indented shoreline, small islands, and relatively undeveloped natural scenery.
  • 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_69e11e4a0ad08190a385b4d343cf6524 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157d08b148190a9a4e445e8579219 completed April 29, 2026, 12:58 a.m.
Created at: April 16, 2026, 8:44 p.m.