Triple

T19921452
Position Surface form Disambiguated ID Type / Status
Subject Bell H-13 Sioux E478804 entity
Predicate hasVariant P455 FINISHED
Object H-13K
The H-13K is a variant of the Bell H-13 Sioux light utility helicopter, used primarily for training, observation, and liaison roles.
 E1411185 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: H-13K | Statement: [Bell H-13 Sioux, hasVariant, H-13K]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: H-13K
Context triple: [Bell H-13 Sioux, hasVariant, H-13K]
  • A. H-13E
    The H-13E is a variant of the Bell H-13 Sioux light utility helicopter, used primarily for training, observation, and medical evacuation roles in the mid-20th century.
  • B. H-13B
    The H-13B is an early production variant of the Bell H-13 Sioux light utility helicopter, used primarily for training, observation, and liaison roles.
  • C. H-13D
    The H-13D is a variant of the Bell H-13 Sioux light utility helicopter, used primarily for observation, training, and medical evacuation roles in the mid-20th century.
  • D. H-13H
    The H-13H is a variant of the Bell H-13 Sioux light utility and observation helicopter, used primarily for training and liaison roles.
  • E. H-13G
    The H-13G is a variant of the Bell H-13 Sioux light utility and observation helicopter, used primarily for liaison, training, and reconnaissance roles.
  • 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: H-13K
Triple: [Bell H-13 Sioux, hasVariant, H-13K]
Generated description
The H-13K is a variant of the Bell H-13 Sioux light utility helicopter, used primarily for training, observation, and liaison roles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: H-13K
Target entity description: The H-13K is a variant of the Bell H-13 Sioux light utility helicopter, used primarily for training, observation, and liaison roles.
  • A. H-13E
    The H-13E is a variant of the Bell H-13 Sioux light utility helicopter, used primarily for training, observation, and medical evacuation roles in the mid-20th century.
  • B. H-13B
    The H-13B is an early production variant of the Bell H-13 Sioux light utility helicopter, used primarily for training, observation, and liaison roles.
  • C. H-13D
    The H-13D is a variant of the Bell H-13 Sioux light utility helicopter, used primarily for observation, training, and medical evacuation roles in the mid-20th century.
  • D. H-13H
    The H-13H is a variant of the Bell H-13 Sioux light utility and observation helicopter, used primarily for training and liaison roles.
  • E. H-13G
    The H-13G is a variant of the Bell H-13 Sioux light utility and observation helicopter, used primarily for liaison, training, and reconnaissance roles.
  • 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659c564788190a3893fc73fc4922b completed April 20, 2026, 4:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0826f62a248190b8c6bb456ca6d519 completed May 16, 2026, 8:12 a.m.
NEDg Description generation batch_6a0827e191688190bc8edf89d4731989 completed May 16, 2026, 8:16 a.m.
NED2 Entity disambiguation (via description) batch_6a08284513a88190bead3da8ba7890dd completed May 16, 2026, 8:18 a.m.
Created at: April 10, 2026, 1:53 p.m.