Triple

T6332284
Position Surface form Disambiguated ID Type / Status
Subject Timor Tengah Selatan Regency E142408 entity
Predicate hasSettlement P1068 FINISHED
Object Soe E585790 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: Soe | Statement: [Timor Tengah Selatan Regency, hasSettlement, Soe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soe
Context triple: [Timor Tengah Selatan Regency, hasSettlement, Soe]
  • A. Soe chosen
    Soe is a town in West Timor, Indonesia, known as an administrative and commercial center in the island’s interior highlands.
  • B. SOE
    SOE was a secret British World War II organization responsible for espionage, sabotage, and supporting resistance movements in enemy-occupied territories.
  • C. Sozh
    The Sozh is a major river in Eastern Europe that flows through Russia, Belarus, and Ukraine before joining the Dnieper.
  • D. Sochalien
    Sochalien is the French demonym for an inhabitant or native of the town of Sochaux in eastern France.
  • E. Sylko
    Sylko is a brand of sewing and embroidery threads historically associated with the textile company J. & P. Coats.
  • 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_69c008d4d8e88190ad301c05b08722ac completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0651634b08190b54860ba0a70f5c4 completed March 22, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62d412bc88190aa8ee0a40ec8bc30 completed March 27, 2026, 7:09 a.m.
Created at: March 22, 2026, 4:30 p.m.