Triple

T18034538
Position Surface form Disambiguated ID Type / Status
Subject AKEL E431472 entity
Predicate shortName P43 FINISHED
Object AKEL 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: AKEL | Statement: [AKEL, shortName, AKEL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AKEL
Context triple: [AKEL, shortName, AKEL]
  • A. AKEL chosen
    AKEL is a major left-wing political party in Cyprus known for its communist roots and strong influence in the country’s political life.
  • B. AKK
    AKK is the IATA airport code for Akhiok Airport, a small public airport serving the community of Akhiok in Alaska, United States.
  • C. AKP
    AKP is the IATA airport code for Anaktuvuk Pass Airport, a small public airport serving the remote village of Anaktuvuk Pass in northern Alaska, United States.
  • D. Osa-AKM
    The Osa-AKM is a Soviet-era self-propelled, short-range surface-to-air missile system designed to provide mobile air defense against low-flying aircraft and helicopters.
  • E. AK Party
    The AK Party is a major conservative political party in Turkey that has dominated the country’s politics since the early 2000s under the leadership of Recep Tayyip Erdoğan.
  • 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_69d8b9050fb48190890155145deb0a66 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4be38766c8190ae95701f4575469c completed April 19, 2026, 11:36 a.m.
Created at: April 10, 2026, 10:25 a.m.