Triple

T12948102
Position Surface form Disambiguated ID Type / Status
Subject Yazd Province E309820 entity
Predicate hasCity P316 FINISHED
Object Abarkuh
Abarkuh is a historic desert city in central Iran known for its ancient cypress tree and traditional mud-brick architecture.
E1011495 NE FINISHED

How this triple was built (4 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: Abarkuh | Statement: [Yazd Province, hasCity, Abarkuh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abarkuh
Context triple: [Yazd Province, hasCity, Abarkuh]
  • A. Jakharrah
    Jakharrah is a settlement located in Libya’s Al Wahat District, an eastern region known for its desert landscapes and oases.
  • B. Abhar
    Abhar is a city in northwestern Iran known for its historical significance and its location along the route between Tehran and Tabriz.
  • C. Khaf
    Khaf is a city in northeastern Iran known for its location in Razavi Khorasan Province near the border with Afghanistan.
  • D. Shemshak
    Shemshak is a mountain village and ski resort in the Alborz range of northern Iran, known for its steep slopes and popularity among advanced skiers.
  • E. Degahabur
    Degahabur is a town in eastern Ethiopia that serves as an administrative and commercial center within the Somali Region.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Abarkuh
Triple: [Yazd Province, hasCity, Abarkuh]
Generated description
Abarkuh is a historic desert city in central Iran known for its ancient cypress tree and traditional mud-brick architecture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Abarkuh
Target entity description: Abarkuh is a historic desert city in central Iran known for its ancient cypress tree and traditional mud-brick architecture.
  • A. Jakharrah
    Jakharrah is a settlement located in Libya’s Al Wahat District, an eastern region known for its desert landscapes and oases.
  • B. Abhar
    Abhar is a city in northwestern Iran known for its historical significance and its location along the route between Tehran and Tabriz.
  • C. Khaf
    Khaf is a city in northeastern Iran known for its location in Razavi Khorasan Province near the border with Afghanistan.
  • D. Shemshak
    Shemshak is a mountain village and ski resort in the Alborz range of northern Iran, known for its steep slopes and popularity among advanced skiers.
  • E. Degahabur
    Degahabur is a town in eastern Ethiopia that serves as an administrative and commercial center within the Somali Region.
  • F. None of above. chosen

Provenance (5 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_69d7bdfb57a88190836b743e2825feca completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97e1c67b8819094e5243267f93ce2 completed April 10, 2026, 10:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af7790808190826f98e8aff01523 completed May 3, 2026, 2:14 a.m.
NEDg Description generation batch_69f6b115720481908796955032043530 completed May 3, 2026, 2:21 a.m.
NED2 Entity disambiguation (via description) batch_69f6b1ea3d288190875888be8356da48 completed May 3, 2026, 2:24 a.m.
Created at: April 9, 2026, 5:43 p.m.