Triple

T22119797
Position Surface form Disambiguated ID Type / Status
Subject Loures E546634 entity
Predicate ISO3166-2 P189 FINISHED
Object PT-LIS 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: PT-LIS | Statement: [Loures, ISO3166-2, PT-LIS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PT-LIS
Context triple: [Loures, ISO3166-2, PT-LIS]
  • A. PTLIS chosen
    PTLIS is the UN/LOCODE designation for the port and city of Lisbon, Portugal, used in international trade and transport documentation.
  • B. LIS
    LIS is the three-letter IATA airport code for Humberto Delgado Airport, the main international airport serving Lisbon, Portugal.
  • C. LIS
    LIS is a U.S. Medicare program that helps low-income beneficiaries pay for their Medicare Part D prescription drug costs.
  • D. LSP
    LSP is a melodramatic, floating purple princess from the Lumpy Space dimension in the animated series "Adventure Time."
  • E. LSP
    LSP is the abbreviation commonly used for the Liberal State Party, a political organization associated with liberal ideology.
  • 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_69e11e38b3848190ac3a4fa97d56e65a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12950f5348190b204fbc347fd5dab completed April 28, 2026, 9:40 p.m.
Created at: April 16, 2026, 8:31 p.m.