Triple

T3778876
Position Surface form Disambiguated ID Type / Status
Subject Seri E83371 entity
Predicate autonym P1435 FINISHED
Object Comcaac E372429 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: Comcaac | Statement: [Seri, autonym, Comcaac]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Comcaac
Context triple: [Seri, autonym, Comcaac]
  • A. Chicomuceltec
    Chicomuceltec was an extinct Mayan language once spoken in parts of Chiapas, Mexico, closely related to Huastec and known from limited historical documentation.
  • B. Muspilli
    Muspilli is an Old High German eschatological poem that vividly depicts the Last Judgment and the end of the world.
  • C. Akatek
    Akatek is a Mayan language spoken primarily by indigenous communities in the highlands of Guatemala.
  • D. Cochimí chosen
    Cochimí were an Indigenous people of the Baja California Peninsula in Mexico, known for their distinct language and traditional hunter-gatherer lifestyle.
  • E. Ixcatec
    Ixcatec is an indigenous Oto-Manguean language of Mexico spoken by a very small and endangered community in Oaxaca.
  • 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_69ad8b235e608190b5a2b1d1bfcef50b completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcc78173081908b230017834cdf9e completed March 8, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4f03d3df48190a4b2382059b7bb24 completed March 14, 2026, 5:21 a.m.
Created at: March 8, 2026, 3:36 p.m.