Triple

T19170961
Position Surface form Disambiguated ID Type / Status
Subject Balqa Governorate E469316 entity
Predicate hasUrbanCenter P2106 FINISHED
Object Mahis 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: Mahis | Statement: [Balqa Governorate, hasUrbanCenter, Mahis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mahis
Context triple: [Balqa Governorate, hasUrbanCenter, Mahis]
  • A. Mahis chosen
    Mahis is a town in Jordan known for its scenic highland setting and proximity to the capital, Amman.
  • B. Mahur
    Mahur is a small town in the Dima Hasao district of Assam, India, known as a local commercial and transport hub in the region’s hilly terrain.
  • C. Mahur
    Mahur is a small settlement located in the Lihir Islands of Papua New Guinea, known for its remote island community and proximity to major gold mining operations.
  • D. Masis
    Masis is the Armenian name for Mount Ararat, the iconic snow-capped volcanic massif that is a national symbol of Armenia and traditionally associated with the biblical story of Noah's Ark.
  • E. Mahres
    Mahres is a coastal town in eastern Tunisia situated along the Gulf of Gabès.
  • 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_69d8dd09d5a081909ae43c286651ae5a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f163c5888190b4880471d17b4f51 completed April 20, 2026, 9:26 a.m.
Created at: April 10, 2026, 12:06 p.m.