Triple

T19823786
Position Surface form Disambiguated ID Type / Status
Subject Bulolo Valley E476264 entity
Predicate locatedNear P294 FINISHED
Object Lae 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: Lae | Statement: [Bulolo Valley, locatedNear, Lae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lae
Context triple: [Bulolo Valley, locatedNear, Lae]
  • A. Lae chosen
    Lae is a major port city on the northeastern coast of Papua New Guinea that served as a key strategic site during World War II and is now an important commercial and industrial center.
  • B. Port of Lae
    The Port of Lae is Papua New Guinea’s largest and busiest seaport, serving as a key commercial and logistics hub for the country’s imports, exports, and coastal shipping.
  • C. Port Moresby
    Port Moresby is the largest city and main economic and administrative center of Papua New Guinea, located on the southeastern coast of the island of New Guinea.
  • D. Port Vila
    Port Vila is the capital and largest city of Vanuatu, located on the island of Efate in the South Pacific.
  • E. Lae Nadzab Airport
    Lae Nadzab Airport is the main commercial airport serving the city of Lae in Morobe Province, Papua New Guinea.
  • 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_69d8e51c7c188190b926f3a2a7b5f881 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6550070c4819099e1f057b9a8849e completed April 20, 2026, 4:32 p.m.
Created at: April 10, 2026, 1:50 p.m.