Triple

T16549935
Position Surface form Disambiguated ID Type / Status
Subject Ozelonacaxtla Totonac E402043 entity
Predicate hasAncestor P369 FINISHED
Object Proto-Totonacan E241837 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: Proto-Totonacan | Statement: [Ozelonacaxtla Totonac, hasAncestor, Proto-Totonacan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Proto-Totonacan
Context triple: [Ozelonacaxtla Totonac, hasAncestor, Proto-Totonacan]
  • A. Totonac languages chosen
    Totonac languages are an indigenous language family of eastern Mexico spoken primarily by the Totonac people in the states of Veracruz, Puebla, and Hidalgo.
  • B. Central Totonac
    Central Totonac is a major variety of the Totonac language spoken in central regions of Veracruz, Mexico, distinct enough from other Totonac varieties to be considered a separate language.
  • C. Proto-Aztecan
    Proto-Aztecan is the hypothesized common ancestor language of the Aztecan (Uto-Aztecan) language family, reconstructed through comparative analysis of its descendant languages.
  • D. Proto-Zoquean
    Proto-Zoquean is the reconstructed common ancestor of the Zoquean branch of the Mixe–Zoquean language family, from which languages like Sierra Popoluca descend.
  • E. Proto-Mayan
    Proto-Mayan is the reconstructed common ancestor of all Mayan languages, from which branches like Wastek and others historically developed.
  • 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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e34fc451dc8190b571d5010f4017f4 completed April 18, 2026, 9:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00758f97708190a289da0bd5d5c254 completed May 10, 2026, 12:09 p.m.
Created at: April 10, 2026, 5:15 a.m.