Triple

T15708811
Position Surface form Disambiguated ID Type / Status
Subject Alamut period E380780 entity
Predicate hasFortress P11932 FINISHED
Object Girdkuh
Girdkuh was a significant mountain fortress associated with the Nizari Ismaili state during the Alamut period in medieval Iran.
E1174041 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: Girdkuh | Statement: [Alamut period, hasFortress, Girdkuh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Girdkuh
Context triple: [Alamut period, hasFortress, Girdkuh]
  • A. Garmeh
    Garmeh is a small city in northeastern Iran, located within North Khorasan Province.
  • B. Bavanat
    Bavanat is a small city in southern Iran known for its traditional rural landscapes, gardens, and location within the mountainous region of Fars Province.
  • C. Sarbisheh
    Sarbisheh is a city in eastern Iran that serves as a local administrative and population center within South Khorasan Province.
  • D. Pishva
    Pishva is a city in Tehran Province, Iran, known as an administrative and local commercial center for the surrounding region.
  • E. Kangavar
    Kangavar is a historic town in western Iran, known for its archaeological remains including a large terraced complex traditionally associated with a temple of Anahita.
  • 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: Girdkuh
Triple: [Alamut period, hasFortress, Girdkuh]
Generated description
Girdkuh was a significant mountain fortress associated with the Nizari Ismaili state during the Alamut period in medieval Iran.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Girdkuh
Target entity description: Girdkuh was a significant mountain fortress associated with the Nizari Ismaili state during the Alamut period in medieval Iran.
  • A. Garmeh
    Garmeh is a small city in northeastern Iran, located within North Khorasan Province.
  • B. Bavanat
    Bavanat is a small city in southern Iran known for its traditional rural landscapes, gardens, and location within the mountainous region of Fars Province.
  • C. Sarbisheh
    Sarbisheh is a city in eastern Iran that serves as a local administrative and population center within South Khorasan Province.
  • D. Pishva
    Pishva is a city in Tehran Province, Iran, known as an administrative and local commercial center for the surrounding region.
  • E. Kangavar
    Kangavar is a historic town in western Iran, known for its archaeological remains including a large terraced complex traditionally associated with a temple of Anahita.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f8d8b648190842c635f2ae7bfa4 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82f22fc88190820ecb171041136d completed May 9, 2026, 6:54 p.m.
NEDg Description generation batch_69ff83ff8c7481909fbc502143c1852f completed May 9, 2026, 6:59 p.m.
NED2 Entity disambiguation (via description) batch_69ff846436e48190b711da134c9a3b81 completed May 9, 2026, 7 p.m.
Created at: April 10, 2026, 4:45 a.m.