Triple

T14578605
Position Surface form Disambiguated ID Type / Status
Subject Saada region E342124 entity
Predicate hasCity P316 FINISHED
Object Kitaf
Kitaf is a town in Yemen's Saada Governorate, known for its location in the country's mountainous northern region.
 E1105875 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: Kitaf | Statement: [Saada region, hasCity, Kitaf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kitaf
Context triple: [Saada region, hasCity, Kitaf]
  • A. Kitob
    Kitob is a town and district-level administrative center in Uzbekistan’s Qashqadaryo Region.
  • B. Kitbuqa
    Kitbuqa was a prominent 13th-century Mongol general and lieutenant of Hulagu Khan, known for leading Mongol forces in the Levant and being killed during their defeat by the Mamluks at the Battle of Ain Jalut.
  • C. Kitihawa
    Kitihawa was a Potawatomi woman historically recognized as the Indigenous wife and business partner of Chicago’s founder, Jean Baptiste Point du Sable.
  • D. Mushaf
    Mushaf is the compiled, written form of the Qur’an, consisting of all its chapters and verses arranged in a fixed canonical order.
  • E. Maktub
    Maktub is a concept from Paulo Coelho’s novel *The Alchemist* expressing the idea that certain events are “written” or destined to happen.
  • 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: Kitaf
Triple: [Saada region, hasCity, Kitaf]
Generated description
Kitaf is a town in Yemen's Saada Governorate, known for its location in the country's mountainous northern region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kitaf
Target entity description: Kitaf is a town in Yemen's Saada Governorate, known for its location in the country's mountainous northern region.
  • A. Kitob
    Kitob is a town and district-level administrative center in Uzbekistan’s Qashqadaryo Region.
  • B. Kitbuqa
    Kitbuqa was a prominent 13th-century Mongol general and lieutenant of Hulagu Khan, known for leading Mongol forces in the Levant and being killed during their defeat by the Mamluks at the Battle of Ain Jalut.
  • C. Kitihawa
    Kitihawa was a Potawatomi woman historically recognized as the Indigenous wife and business partner of Chicago’s founder, Jean Baptiste Point du Sable.
  • D. Mushaf
    Mushaf is the compiled, written form of the Qur’an, consisting of all its chapters and verses arranged in a fixed canonical order.
  • E. Maktub
    Maktub is a concept from Paulo Coelho’s novel *The Alchemist* expressing the idea that certain events are “written” or destined to happen.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb3f6f78c81908a30ecb4c025299d completed April 14, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8ad03e7881908a783182c6d656b5 completed May 8, 2026, 7:03 a.m.
NEDg Description generation batch_69fd8c278e8481909465972b32ad6c28 completed May 8, 2026, 7:09 a.m.
NED2 Entity disambiguation (via description) batch_69fd8ca921108190943eb948f9af6123 completed May 8, 2026, 7:11 a.m.
Created at: April 10, 2026, 1:24 a.m.