Triple

T9186573
Position Surface form Disambiguated ID Type / Status
Subject Western Iranian languages E220473 entity
Predicate hasHistoricalSubdivision P5057 FINISHED
Object Median language E332075 NE FINISHED

How this triple was built (3 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: Median language | Statement: [Western Iranian languages, hasHistoricalSubdivision, Median language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Median language
Context triple: [Western Iranian languages, hasHistoricalSubdivision, Median language]
  • A. Median language chosen
    Median language was an ancient Northwestern Iranian language spoken by the Medes in what is now Iran during the first millennium BCE.
  • B. Mixe languages
    Mixe languages are a group of related indigenous Mesoamerican languages spoken primarily by the Mixe people in the highlands of Oaxaca, Mexico.
  • C. Mon language
    Mon language is an Austroasiatic language historically spoken in parts of Myanmar and Thailand, notable for its ancient literary tradition and influence on regional scripts and cultures.
  • D. Even language
    Even is a Northern Tungusic language spoken by the Even people of northeastern Siberia in Russia.
  • E. Language
    Language is a leading peer-reviewed linguistics journal known for publishing influential research and critical reviews in the field, including Noam Chomsky’s landmark 1959 critique of behaviorist theories.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasHistoricalSubdivision
Context triple: [Western Iranian languages, hasHistoricalSubdivision, Median language]
  • A. hasHistoricTerritory
    Indicates that an entity possesses or claims a territory that it historically occupied, controlled, or was associated with in the past.
  • B. historicallyDividedInto
    Indicates that an entity was separated into multiple distinct parts or regions during a past historical period.
  • C. historicallyPartOf chosen
    Indicates that one entity was formerly a component, region, or subdivision of another entity during a past historical period, but is not necessarily part of it in the present.
  • D. hasHadMultipleDistrictsHistorically
    Indicates that an entity has been divided into more than one district at different times in its history.
  • E. formerSubdivisionOf
    Indicates that an entity once functioned as an administrative or territorial part of another entity but no longer holds that status.
  • F. None of above.

Provenance (4 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_69ca83e6d77c81909862b7afef56b1bf completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccc31a52508190a83ccd76f3aa039b completed April 1, 2026, 7:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05c1e163c8190bf9a85de7569c14d completed April 4, 2026, 12:32 a.m.
PD Predicate disambiguation batch_69cc66090e5881908889dc1213815626 completed April 1, 2026, 12:25 a.m.
Created at: March 30, 2026, 7:24 p.m.