Triple

T15585016
Position Surface form Disambiguated ID Type / Status
Subject Wahidi Sultanates E374595 entity
Predicate capital P234 FINISHED
Object Haban
Haban is a historic town in eastern Yemen that once served as the political and commercial center of the Wahidi Sultanates in the Hadhramaut region.
 E1165704 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: Haban | Statement: [Wahidi Sultanates, capital, Haban]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Haban
Context triple: [Wahidi Sultanates, capital, Haban]
  • A. Habana Goya
    Habana Goya is a graphics processing unit (GPU) architecture developed by Habana Labs, primarily designed to accelerate deep learning inference workloads in data centers.
  • B. Haría
    Haría is a picturesque municipality and village in the northern part of Lanzarote in Spain’s Canary Islands, known for its lush “Valley of a Thousand Palms” and traditional architecture.
  • C. Wanka
    Wanka is a song featured on the album "Legend of the Sun Virgin" by New Zealand singer-songwriter Bic Runga.
  • D. Guane
    Guane is a small town and municipality in western Cuba known for its rural character and tobacco-growing traditions.
  • E. Guane
    Guane is a small, historic village in Colombia’s Santander department, known for its preserved colonial architecture and tranquil rural atmosphere.
  • 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: Haban
Triple: [Wahidi Sultanates, capital, Haban]
Generated description
Haban is a historic town in eastern Yemen that once served as the political and commercial center of the Wahidi Sultanates in the Hadhramaut region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Haban
Target entity description: Haban is a historic town in eastern Yemen that once served as the political and commercial center of the Wahidi Sultanates in the Hadhramaut region.
  • A. Habana Goya
    Habana Goya is a graphics processing unit (GPU) architecture developed by Habana Labs, primarily designed to accelerate deep learning inference workloads in data centers.
  • B. Haría
    Haría is a picturesque municipality and village in the northern part of Lanzarote in Spain’s Canary Islands, known for its lush “Valley of a Thousand Palms” and traditional architecture.
  • C. Wanka
    Wanka is a song featured on the album "Legend of the Sun Virgin" by New Zealand singer-songwriter Bic Runga.
  • D. Guane
    Guane is a small town and municipality in western Cuba known for its rural character and tobacco-growing traditions.
  • E. Guane
    Guane is a small, historic village in Colombia’s Santander department, known for its preserved colonial architecture and tranquil rural atmosphere.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e47971481909e986dd999354628 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4f71e48190a15eb0a2138f083f completed May 9, 2026, 3:01 p.m.
NEDg Description generation batch_69ff4fb2522481909fa66c2e1fac23bf completed May 9, 2026, 3:16 p.m.
NED2 Entity disambiguation (via description) batch_69ff5238f0e88190b280942022480c12 completed May 9, 2026, 3:26 p.m.
Created at: April 10, 2026, 4:11 a.m.