Triple

T17034070
Position Surface form Disambiguated ID Type / Status
Subject Val-de-Reuil E413273 entity
Predicate hasTwinTown P919 FINISHED
Object Kefraya E1111251 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: Kefraya | Statement: [Val-de-Reuil, hasTwinTown, Kefraya]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kefraya
Context triple: [Val-de-Reuil, hasTwinTown, Kefraya]
  • A. Ain El Mreisseh
    Ain El Mreisseh is a coastal neighborhood in Beirut, Lebanon, known for its seaside promenade, hotels, and proximity to the city’s central districts.
  • B. Naqoura
    Naqoura is a coastal town in southern Lebanon that serves as a strategic location and headquarters for the United Nations Interim Force in Lebanon (UNIFIL).
  • C. Umm al-Ghanam
    Umm al-Ghanam is a village in northern Israel that forms part of the Arab local council of Shibli–Umm al-Ghanam near Mount Tabor.
  • D. Kfarhay chosen
    Kfarhay is a small village located in the Batroun District of northern Lebanon, known for its rural character and traditional Lebanese landscape.
  • E. Ayn al-Jarr
    Ayn al-Jarr is the ancient spring whose name is believed to have given rise to the name of the Lebanese town of Anjar.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8eea4448190bd2eed88de2b4e73 completed April 18, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b59ad3c8190914ee6f8c903cbbf completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.