Triple

T21334816
Position Surface form Disambiguated ID Type / Status
Subject Yale romanization of Cantonese E526012 entity
Predicate ISO15924Script P11937 FINISHED
Object Latn NE NERFINISHED

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: Latn | Statement: [Yale romanization of Cantonese, ISO15924Script, Latn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Latn
Context triple: [Yale romanization of Cantonese, ISO15924Script, Latn]
  • A. Latn chosen
    Latn is the ISO 15924 script code representing the Latin alphabet used for writing numerous modern languages worldwide.
  • B. Latuvi
    Latuvi is a small rural village in the Sierra Norte region of Oaxaca, Mexico, known for its mountainous landscapes and traditional indigenous culture.
  • C. Latynina
    Latynina is a Russian surname most famously associated with Larisa Latynina, one of the most decorated gymnasts in Olympic history.
  • D. Latgalian
    Latgalian is an Eastern Baltic language variety closely related to Latvian, traditionally spoken by the Latgalian ethnic group in the Latgale region of eastern Latvia.
  • E. Latverian
    Latverian refers to something or someone from Latveria, the fictional Eastern European nation ruled by Doctor Doom in Marvel Comics.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b51b90788190a4dd823d962626da completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e898d602c08190821c63e0aff42fc2 completed April 22, 2026, 9:45 a.m.
Created at: April 16, 2026, 4:43 p.m.