Triple

T14032372
Position Surface form Disambiguated ID Type / Status
Subject LLHA E337622 entity
Predicate identifies P310 FINISHED
Object Haifa Airport E67458 NE FINISHED

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: Haifa Airport | Statement: [LLHA, identifies, Haifa Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haifa Airport
Context triple: [LLHA, identifies, Haifa Airport]
  • A. Haifa Airport chosen
    Haifa Airport is a small international airport in northern Israel serving domestic flights and limited regional routes for the city of Haifa.
  • B. Eilat Airport
    Eilat Airport was a small domestic airport that served the resort city of Eilat in southern Israel until its closure and replacement by Ramon Airport.
  • C. Orly Airport
    Orly Airport is a major international airport serving Paris, France, located south of the city and handling a large share of its domestic and European flights.
  • D. Ozar Airport
    Ozar Airport is a public airport serving the city of Nashik in Maharashtra, India, handling both civilian and limited military aviation operations.
  • E. Ben-Gurion Airport
    Ben-Gurion Airport is Israel’s main international airport, located near Tel Aviv and serving as the country’s primary gateway for global air travel.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2fab17008190981f1808726fa11c completed April 14, 2026, 12:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb657ab348190ab51ec0e8caa2c4f completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:20 p.m.