Triple

T5131270
Position Surface form Disambiguated ID Type / Status
Subject French Hill E115704 entity
Predicate near P350 FINISHED
Object Mount Scopus E45693 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: Mount Scopus | Statement: [French Hill, near, Mount Scopus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mount Scopus
Context triple: [French Hill, near, Mount Scopus]
  • A. Mount Scopus chosen
    Mount Scopus is a prominent hill in northeastern Jerusalem known for its historic significance, panoramic views, and the campus of the Hebrew University of Jerusalem.
  • B. Shaar HaTziyun
    Shaar HaTziyun is a detailed commentary and source-reference work by Rabbi Yisrael Meir Kagan that accompanies the Mishnah Berurah on the Shulchan Aruch, Orach Chaim.
  • C. Temple Mount
    Temple Mount is a hilltop in Jerusalem revered as one of the holiest sites in Judaism, traditionally regarded as the location of the First and Second Temples.
  • D. Mount Herzl
    Mount Herzl is Israel’s national cemetery and a central memorial site in Jerusalem, serving as the burial place of prominent leaders and fallen soldiers.
  • E. White Tower of Ramla
    The White Tower of Ramla is a prominent medieval stone minaret and lookout tower in the Israeli city of Ramla, known for its striking architecture and panoramic views.
  • 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_69bd444426bc819099ccd23f141e22aa completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd782904788190b544540483915c0e completed March 20, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed91b5a44819096e1cc045f061db9 completed March 21, 2026, 5:44 p.m.
Created at: March 20, 2026, 1:42 p.m.