Triple

T12601342
Position Surface form Disambiguated ID Type / Status
Subject Yahsat E300864 entity
Predicate hasSubsidiary P254 FINISHED
Object YahService
YahService is a subsidiary company of the UAE-based satellite operator Yahsat, providing satellite communication and related services.
E991938 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: YahService | Statement: [Yahsat, hasSubsidiary, YahService]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: YahService
Context triple: [Yahsat, hasSubsidiary, YahService]
  • A. Yah
    Yah is a shortened form of the Hebrew divine name often used in religious texts and songs to refer to the God of Israel.
  • B. YAI
    YAI is the IATA airport code for General Bernardo O'Higgins Airport serving the city of Chillán in Chile.
  • C. YAM
    YAM is the IATA airport code for Sault Ste. Marie Airport in Ontario, Canada.
  • D. YAYE
    YAYE is the ICAO airport code for Ayers Rock Airport, which serves the Uluru (Ayers Rock) region in Australia's Northern Territory.
  • E. YADYOK
    YADYOK is the School of Foreign Languages at Boğaziçi University, responsible for language education and preparatory English programs.
  • 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: YahService
Triple: [Yahsat, hasSubsidiary, YahService]
Generated description
YahService is a subsidiary company of the UAE-based satellite operator Yahsat, providing satellite communication and related services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: YahService
Target entity description: YahService is a subsidiary company of the UAE-based satellite operator Yahsat, providing satellite communication and related services.
  • A. Yah
    Yah is a shortened form of the Hebrew divine name often used in religious texts and songs to refer to the God of Israel.
  • B. YAI
    YAI is the IATA airport code for General Bernardo O'Higgins Airport serving the city of Chillán in Chile.
  • C. YAM
    YAM is the IATA airport code for Sault Ste. Marie Airport in Ontario, Canada.
  • D. YAYE
    YAYE is the ICAO airport code for Ayers Rock Airport, which serves the Uluru (Ayers Rock) region in Australia's Northern Territory.
  • E. YADYOK
    YADYOK is the School of Foreign Languages at Boğaziçi University, responsible for language education and preparatory English programs.
  • 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_69d7bdea2ca881908f379526c13b1145 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954d1f6ac8190ab21ca7bcbc80129 completed April 10, 2026, 7:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65ec92c6c8190bd2d193e70940407 completed May 2, 2026, 8:30 p.m.
NEDg Description generation batch_69f65faf33e0819092df07a5fa98cb73 completed May 2, 2026, 8:33 p.m.
NED2 Entity disambiguation (via description) batch_69f66036f520819098af75cd5578d573 completed May 2, 2026, 8:36 p.m.
Created at: April 9, 2026, 5:09 p.m.