Triple

T23217582
Position Surface form Disambiguated ID Type / Status
Subject Umm al-Fahm E580792 entity
Predicate locatedSoutheastOf P5143 FINISHED
Object Haifa 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: Haifa | Statement: [Umm al-Fahm, locatedSoutheastOf, Haifa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haifa
Context triple: [Umm al-Fahm, locatedSoutheastOf, Haifa]
  • A. Haifa chosen
    Haifa is a major Israeli city on the Mediterranean coast, known for its significant port, mixed Jewish-Arab population, and the terraced Baháʼí Gardens on Mount Carmel.
  • B. Ashdod
    Ashdod is a major coastal city in southern Israel that serves as an important cultural and religious hub, including for the Karaite Jewish community.
  • C. Ramla
    Ramla is an Israeli city historically significant as a major religious and communal center for Karaite Jews.
  • D. Tel Aviv
    Tel Aviv is a major Israeli coastal city known for its vibrant nightlife, high-tech industry, and modernist architecture.
  • E. Reḥovot
    Reḥovot is the modern Hebrew name for the ancient biblical city of Rehoboth, mentioned in the Hebrew Bible as a place associated with the patriarch Isaac.
  • 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_69e2460389408190be74f41d217799a9 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1916653f08190a7dcbc659c6b6a25 completed April 29, 2026, 5:04 a.m.
Created at: April 17, 2026, 4:08 p.m.