Triple

T21661779
Position Surface form Disambiguated ID Type / Status
Subject Beirut Governorate E534610 entity
Predicate contains P35 FINISHED
Object Mar Mikhael 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: Mar Mikhael | Statement: [Beirut Governorate, contains, Mar Mikhael]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mar Mikhael
Context triple: [Beirut Governorate, contains, Mar Mikhael]
  • A. Mar Mikhael chosen
    Mar Mikhael is a historically vibrant Beirut neighborhood known for its nightlife, arts scene, and distinctive old buildings, many of which were devastated in the 2020 port explosion.
  • B. Mikhalis
    Mikhalis is the birth name of Makarios III, the influential Archbishop and first President of independent Cyprus.
  • C. Кальмиус
    Кальмиус — это река на востоке Украины, протекающая через Донецкую область и впадающая в Азовское море.
  • D. San-Nicolao
    San-Nicolao is a coastal commune on the island of Corsica in France, known for its Mediterranean scenery and tourism.
  • E. Mikleuš
    Mikleuš is a small municipality and village in northeastern Croatia, situated within the Virovitica-Podravina region.
  • 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_69e0c467e1f48190af2650b19175abc4 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef6c0883d481908dfdc66832c34d74 completed April 27, 2026, 2 p.m.
Created at: April 16, 2026, 6:36 p.m.