Triple

T14521810
Position Surface form Disambiguated ID Type / Status
Subject Somali Airlines E340670 entity
Predicate IATAcode P418 FINISHED
Object HH
HH is the former IATA airline designator assigned to Somali Airlines, the now-defunct national carrier of Somalia.
 E1105136 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: HH | Statement: [Somali Airlines, IATAcode, HH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HH
Context triple: [Somali Airlines, IATAcode, HH]
  • A. HH
    HH is the vehicle registration code used on license plates for the German city-state of Hamburg.
  • B. HH 2
    HH 2 is a well-known Herbig–Haro object consisting of bright nebulous knots formed by jets from a young star colliding with surrounding interstellar gas.
  • C. HH 1
    HH 1 is a well-known Herbig–Haro object, a small, bright patch of nebulosity formed by jets from a newborn star colliding with surrounding interstellar gas and dust.
  • D. HHY
    HHY is the National Rail station code for Highbury & Islington railway station in London, England.
  • E. HUU
    HUU is the students' union representing and supporting students at the University of Hull through services, activities, and advocacy.
  • 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: HH
Triple: [Somali Airlines, IATAcode, HH]
Generated description
HH is the former IATA airline designator assigned to Somali Airlines, the now-defunct national carrier of Somalia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HH
Target entity description: HH is the former IATA airline designator assigned to Somali Airlines, the now-defunct national carrier of Somalia.
  • A. HH
    HH is the vehicle registration code used on license plates for the German city-state of Hamburg.
  • B. HH 2
    HH 2 is a well-known Herbig–Haro object consisting of bright nebulous knots formed by jets from a young star colliding with surrounding interstellar gas.
  • C. HH 1
    HH 1 is a well-known Herbig–Haro object, a small, bright patch of nebulosity formed by jets from a newborn star colliding with surrounding interstellar gas and dust.
  • D. HHY
    HHY is the National Rail station code for Highbury & Islington railway station in London, England.
  • E. HUU
    HUU is the students' union representing and supporting students at the University of Hull through services, activities, and advocacy.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a72cff08190878b4bed9b0b5eb5 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a4da6908190a3e2cae16f6240d9 completed May 8, 2026, 5:53 a.m.
NEDg Description generation batch_69fd7bc384b88190bdf562e68b0c44f6 completed May 8, 2026, 5:59 a.m.
NED2 Entity disambiguation (via description) batch_69fd7c2260808190bced99ed86e8fd4b completed May 8, 2026, 6:01 a.m.
Created at: April 10, 2026, 1:22 a.m.