Triple

T21707633
Position Surface form Disambiguated ID Type / Status
Subject Transjordan E535811 entity
Predicate contains P35 FINISHED
Object Karak 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: Karak | Statement: [Transjordan, contains, Karak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karak
Context triple: [Transjordan, contains, Karak]
  • A. Karak
    Karak is a town in Pakistan’s Khyber Pakhtunkhwa province known as the headquarters of Karak District and for its surrounding oil and gas reserves.
  • B. Karak chosen
    Karak is a historic Jordanian city best known for its imposing Crusader-era castle overlooking the surrounding highlands.
  • C. Karak
    Karak is a red-tailed black cockatoo known for serving as the official mascot of the 2006 Commonwealth Games in Melbourne, Australia.
  • D. Karad
    Karad is a town in the Satara district of Maharashtra, India, known for its location at the confluence of the Krishna and Koyna rivers and its regional commercial and educational significance.
  • E. Karashahr
    Karashahr is an ancient oasis town in Xinjiang, China, historically significant as a Silk Road hub and a key center of the Indo-European–speaking Tocharian culture.
  • 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_69e0c46b44c0819088ab883ebd44e0e8 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efb530779c819080204c3bd2f6afa2 completed April 27, 2026, 7:12 p.m.
Created at: April 16, 2026, 6:46 p.m.