Triple

T5835769
Position Surface form Disambiguated ID Type / Status
Subject Helong E129464 entity
Predicate associatedCity P3207 FINISHED
Object Kupang E124162 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: Kupang | Statement: [Helong, associatedCity, Kupang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kupang
Context triple: [Helong, associatedCity, Kupang]
  • A. Kupang chosen
    Kupang is the capital and largest city of Indonesia’s East Nusa Tenggara province, located on the western part of Timor Island and serving as a key regional port and administrative center.
  • B. Kavieng
    Kavieng is a coastal town in Papua New Guinea known as the main urban and commercial center of New Ireland Province and a gateway to nearby islands and dive sites.
  • C. Ambon
    Ambon is a major city and port in eastern Indonesia, known as an administrative, economic, and cultural hub in the Maluku region.
  • D. Tarakan
    Tarakan is an island off the northeastern coast of Borneo in Indonesia, historically significant for its oil resources and as a strategic battleground during World War II.
  • E. Macassar
    Macassar is the former name of Makassar, a major port city on the island of Sulawesi in Indonesia known historically as an important center of trade and maritime power.
  • 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_69c0084af79c81908af128ccc29983d0 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c034a358708190bfce78e7bd75db36 completed March 22, 2026, 6:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a196ebb88190aea57899be954aae completed March 23, 2026, 2:12 a.m.
Created at: March 22, 2026, 3:54 p.m.