Triple

T21557616
Position Surface form Disambiguated ID Type / Status
Subject Koura E531933 entity
Predicate hasTown P847 FINISHED
Object Balamand 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 | Statement: [Koura, hasTown, Balamand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Balamand
Context triple: [Koura, hasTown, Balamand]
  • A. 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.
  • B. Baalbek
    Baalbek is an ancient city in Lebanon renowned for its monumental Roman temple complex and well-preserved archaeological ruins.
  • C. Ras Baalbek
    Ras Baalbek is a village and archaeological site in northeastern Lebanon, known for its ancient ruins and proximity to the Syrian border.
  • D. Deir el Qamar
    Deir el Qamar is a historic Lebanese village in the Chouf region known for its well-preserved traditional architecture and former role as a political and cultural center of Mount Lebanon.
  • E. Ṭarābulus
    Ṭarābulus is the Arabic name for Tripoli, a major historic port city and the capital of Libya on the Mediterranean coast.
  • 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_69e0c460232c81908de2c3819d17c00e completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eed2e14af88190bc70b4d0f3453aac completed April 27, 2026, 3:07 a.m.
Created at: April 16, 2026, 6:29 p.m.