Triple

T15850149
Position Surface form Disambiguated ID Type / Status
Subject Heshbon E384312 entity
Predicate laterControl P4700 FINISHED
Object Moab E108457 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: Moab | Statement: [Heshbon, laterControl, Moab]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moab
Context triple: [Heshbon, laterControl, Moab]
  • A. Moab chosen
    Moab is an ancient kingdom located east of the Dead Sea, frequently mentioned in the Hebrew Bible as a neighboring land to Israel.
  • B. Moab, Utah
    Moab, Utah is a small southeastern Utah city known as a major gateway for outdoor recreation, especially for visiting nearby national parks and exploring red rock desert landscapes.
  • C. Kanab
    Kanab is a small city in southern Utah known as a gateway to major national parks and scenic red rock landscapes.
  • D. Ouray
    Ouray is a small historic mountain town in southwestern Colorado known for its dramatic alpine scenery, hot springs, and ice climbing.
  • E. Escalante, Utah
    Escalante, Utah is a small gateway town in southern Utah known for its proximity to Grand Staircase–Escalante National Monument and surrounding plateaus, canyons, and desert landscapes.
  • 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_69d86da422088190aac39e32e6c68429 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e14cab0fe48190bd6629e071761e91 completed April 16, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb59bc1f881908c5ed93039e94a46 completed May 9, 2026, 10:30 p.m.
Created at: April 10, 2026, 4:50 a.m.