Triple

T13047144
Position Surface form Disambiguated ID Type / Status
Subject Nakhon Ratchasima E327354 entity
Predicate gatewayTo P423 FINISHED
Object Isan region E327356 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: Isan region | Statement: [Nakhon Ratchasima, gatewayTo, Isan region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isan region
Context triple: [Nakhon Ratchasima, gatewayTo, Isan region]
  • A. Isan chosen
    Isan is a culturally distinct and predominantly rural region in northeastern Thailand known for its Lao-influenced language, cuisine, and traditions.
  • B. Trièves region
    The Trièves region is a rural area in the French Prealps known for its dramatic mountain scenery, traditional villages, and outdoor recreation opportunities.
  • C. Languedoc
    Languedoc is a historic region in southern France known for its Occitan culture, medieval towns, and long-standing wine-making tradition.
  • D. Gascogne
    Gascogne is a historic cultural region in southwestern France known for its Gascon language, rich rural traditions, and distinctive cuisine including Armagnac and foie gras.
  • E. Touraine
    Touraine is a historic region in central France, famed for its Loire Valley châteaux, wine production, and role as a former royal heartland.
  • 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_69d8076e64308190904fb5c93517c901 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d9805125e481908ed56f708de98a9e completed April 10, 2026, 10:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d5fdd04c8190a86dbba1b81c8e6b completed May 3, 2026, 4:58 a.m.
Created at: April 9, 2026, 8:57 p.m.