Triple

T18639455
Position Surface form Disambiguated ID Type / Status
Subject John X of Antioch E455642 entity
Predicate residence P75 FINISHED
Object Balamand, Lebanon 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: Balamand, Lebanon | Statement: [John X of Antioch, residence, Balamand, Lebanon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Balamand, Lebanon
Context triple: [John X of Antioch, residence, Balamand, Lebanon]
  • A. Nabatieh, Lebanon
    Nabatieh is a predominantly Shia Muslim city in southern Lebanon known as a regional political and commercial center and for its major Ashura commemorations.
  • B. Balamand chosen
    Balamand is a locality in northern Lebanon best known for hosting the historic Balamand Monastery and the main campus of the University of Balamand.
  • C. Tayr Dibba, Lebanon
    Tayr Dibba is a village in southern Lebanon known primarily as the birthplace of senior Hezbollah military commander Imad Mughniyeh.
  • D. Amioun, Lebanon
    Amioun, Lebanon is a historic town in northern Lebanon known as the birthplace of scholar and author Nassim Nicholas Taleb and for its ancient churches and olive groves.
  • E. Naqoura, Lebanon
    Naqoura, Lebanon is a coastal town in southern Lebanon best known as the base of operations and headquarters for the United Nations peacekeeping mission UNIFIL.
  • 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_69d8d38ea1e88190997e9b231190ba6f completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54fcbe3088190849f60b09d1e7e4b completed April 19, 2026, 9:57 p.m.
Created at: April 10, 2026, 11:47 a.m.