Triple

T12280010
Position Surface form Disambiguated ID Type / Status
Subject Socotra Airport E292692 entity
Predicate connectsTo P845 FINISHED
Object Seiyun
Seiyun is a historic city in Yemen’s Hadhramaut region, known for its traditional mud-brick architecture and role as a regional cultural and commercial center.
E996199 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: Seiyun | Statement: [Socotra Airport, connectsTo, Seiyun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seiyun
Context triple: [Socotra Airport, connectsTo, Seiyun]
  • A. Yoboki
    Yoboki is a small town in Djibouti located within the Dikhil Region, known for its arid landscape and role as a local administrative and trading center.
  • B. Yachimun
    Yachimun is the traditional Okinawan pottery style known for its rustic forms, vivid glazes, and deep roots in Ryukyuan culture and craftsmanship.
  • C. Emori
    Emori is a Japanese given name that can be used for individuals of any gender.
  • D. Miyazya
    Miyazya is one of the spring months in the Ethiopian calendar, roughly corresponding to April in the Gregorian calendar.
  • E. Yahata
    Yahata was a former city in Fukuoka Prefecture, Japan, that became part of the larger city of Kitakyushu through municipal merger.
  • 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: Seiyun
Triple: [Socotra Airport, connectsTo, Seiyun]
Generated description
Seiyun is a historic city in Yemen’s Hadhramaut region, known for its traditional mud-brick architecture and role as a regional cultural and commercial center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Seiyun
Target entity description: Seiyun is a historic city in Yemen’s Hadhramaut region, known for its traditional mud-brick architecture and role as a regional cultural and commercial center.
  • A. Yoboki
    Yoboki is a small town in Djibouti located within the Dikhil Region, known for its arid landscape and role as a local administrative and trading center.
  • B. Yachimun
    Yachimun is the traditional Okinawan pottery style known for its rustic forms, vivid glazes, and deep roots in Ryukyuan culture and craftsmanship.
  • C. Emori
    Emori is a Japanese given name that can be used for individuals of any gender.
  • D. Miyazya
    Miyazya is one of the spring months in the Ethiopian calendar, roughly corresponding to April in the Gregorian calendar.
  • E. Yahata
    Yahata was a former city in Fukuoka Prefecture, Japan, that became part of the larger city of Kitakyushu through municipal merger.
  • 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_69d6ab690ad081908c0ed3870ec82d53 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cf1ab8c8190a51f498bfda957d8 completed April 10, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6685205608190b504ab6e7c73ee51 completed May 2, 2026, 9:10 p.m.
NEDg Description generation batch_69f669f69fe4819097dfc63780e8587e completed May 2, 2026, 9:17 p.m.
NED2 Entity disambiguation (via description) batch_69f66b619c88819098acbfb60fac9921 completed May 2, 2026, 9:23 p.m.
Created at: April 8, 2026, 9:52 p.m.