Triple

T19302879
Position Surface form Disambiguated ID Type / Status
Subject Roelof Deodati E482745 entity
Predicate employer P7 FINISHED
Object VOC 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: VOC | Statement: [Roelof Deodati, employer, VOC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: VOC
Context triple: [Roelof Deodati, employer, VOC]
  • A. VOC chosen
    VOC is the abbreviation for the Dutch East India Company, a powerful 17th-century trading corporation that dominated European-Asian maritime trade and helped shape early global capitalism.
  • B. VOCL
    VOCL is the ICAO airport code for Calicut International Airport, a major international airport serving Kozhikode in the Indian state of Kerala.
  • C. VOG
    VOG is the IATA airport code for Volgograd International Airport, a regional air transport hub serving the city of Volgograd in Russia.
  • D. VOCB
    VOCB is the ICAO airport code for Coimbatore International Airport in Coimbatore, Tamil Nadu, India.
  • E. VVO
    VVO is the three-letter IATA airport code for Vladivostok International Airport in Russia.
  • 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_69d8e8d04d5c8190baa816986f2b1d1e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc8add788190aed98bcbad518808 completed April 20, 2026, 10:14 a.m.
Created at: April 10, 2026, 1:31 p.m.