Triple

T6935581
Position Surface form Disambiguated ID Type / Status
Subject western Maya lowlands E160545 entity
Predicate locatedIn P40 FINISHED
Object Tabasco E57708 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: Tabasco | Statement: [western Maya lowlands, locatedIn, Tabasco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tabasco
Context triple: [western Maya lowlands, locatedIn, Tabasco]
  • A. Tabasco chosen
    Tabasco is a southeastern Mexican state along the Gulf of Mexico, known for its tropical climate, petroleum industry, and rich wetlands.
  • B. Cholula
    Cholula is a historic Mexican city famed for its Great Pyramid and rich pre-Hispanic and colonial heritage.
  • C. Cayenne
    Cayenne is the principal city and administrative center of French Guiana, located on the Atlantic coast in northeastern South America.
  • D. Manteca
    "Manteca" is a groundbreaking 1947 Afro-Cuban jazz composition co-written by Dizzy Gillespie that became one of the first and most influential Latin jazz standards.
  • E. Manteca
    Manteca is a city in California’s Central Valley known for its agricultural roots, suburban growth, and role as a commuter hub between the Bay Area and inland communities.
  • 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_69c6884e15208190b9e91487eaafcf85 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da429b5c8190a59901e0005a5415 completed March 27, 2026, 7:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69c75151d5e48190b2389ae9049d1454 completed March 28, 2026, 3:56 a.m.
Created at: March 27, 2026, 2:27 p.m.