Triple

T7450855
Position Surface form Disambiguated ID Type / Status
Subject Ruteng E172003 entity
Predicate roadConnectionTo P9041 FINISHED
Object Ende E169783 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: Ende | Statement: [Ruteng, roadConnectionTo, Ende]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ende
Context triple: [Ruteng, roadConnectionTo, Ende]
  • A. Ende chosen
    Ende is a coastal town and regency capital on the Indonesian island of Flores, known as a regional hub and gateway to nearby natural attractions.
  • B. Endere
    Endere is an ancient Silk Road archaeological site in the Taklamakan Desert of Xinjiang, China, known for its ruined fort, Buddhist remains, and Kharosthi and Sanskrit manuscripts.
  • C. Endeis
    Endeis is a figure in Greek mythology known primarily as the mother of the hero Peleus and grandmother of Achilles.
  • D. Endekan
    Endekan is an alternate name for the Enrekang language, an Austronesian language spoken in South Sulawesi, Indonesia.
  • E. Endon
    Endon is a village in Staffordshire, England, known as the birthplace of early 20th-century poet and critic T. E. Hulme.
  • 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_69c68a66554c8190add75c65942c0317 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f38c28e08190956766a5222fe720 completed March 27, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83455d84c8190bd129fda0813dc56 completed March 28, 2026, 8:04 p.m.
Created at: March 27, 2026, 3:14 p.m.