Triple

T7107484
Position Surface form Disambiguated ID Type / Status
Subject Flores, Guatemala E165623 entity
Predicate nearbySite P350 FINISHED
Object Yaxhá E413627 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: Yaxhá | Statement: [Flores, Guatemala, nearbySite, Yaxhá]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yaxhá
Context triple: [Flores, Guatemala, nearbySite, Yaxhá]
  • A. Yaxhá chosen
    Yaxhá is an ancient Maya archaeological site in northern Guatemala known for its large ceremonial complexes and scenic setting beside Lake Yaxhá.
  • B. Yaxuná
    Yaxuná is an ancient Maya archaeological site in Mexico’s Yucatán Peninsula, notable for its long history of occupation and its strategic position within a network of pre-Hispanic causeways.
  • C. Tazmalt
    Tazmalt is a town and commune in northern Algeria known as a local commercial and transport hub within Béjaïa Province.
  • D. Oxlumo
    Oxlumo is an RNA interference (RNAi) therapeutic used to treat primary hyperoxaluria type 1 by reducing hepatic oxalate production.
  • E. Hualaihué
    Hualaihué is a coastal municipality in southern Chile known for its fjords, islands, and location within the Los Lagos Region’s Palena Province.
  • 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_69c6888120f081908f8f01b201dc4a4c completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e5bbd4e481909e0948d01c6b15f4 completed March 27, 2026, 8:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7ad86ac688190af97b42d0cb36b84 completed March 28, 2026, 10:29 a.m.
Created at: March 27, 2026, 2:42 p.m.