Triple

T20518336
Position Surface form Disambiguated ID Type / Status
Subject Hunter-Killer machine E503737 entity
Predicate hasVariant P455 FINISHED
Object HK-Sub
HK-Sub is an aquatic variant of the Terminator franchise’s Hunter-Killer machines, designed for underwater search-and-destroy operations.
 E1436062 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: HK-Sub | Statement: [Hunter-Killer machine, hasVariant, HK-Sub]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HK-Sub
Context triple: [Hunter-Killer machine, hasVariant, HK-Sub]
  • A. HKY
    HKY is the three-letter IATA airport code for Hickory Regional Airport in Hickory, North Carolina, USA.
  • B. Hansu
    Hansu is a central, morally ambiguous Korean businessman in Min Jin Lee’s novel "Pachinko," whose complex relationship with the protagonist’s family drives much of the multigenerational drama.
  • C. HK53
    The HK53 is a compact 5.56×45mm NATO assault rifle developed by Heckler & Koch that combines the roller-delayed blowback system of the G3 family with the size and handling of a submachine gun.
  • D. KMHK
    KMHK is the ICAO airport code for Manhattan Regional Airport, a public airport serving Manhattan, Kansas, in the United States.
  • E. KLHK
    KLHK is the Indonesian government ministry responsible for environmental protection, natural resource management, and forestry policy.
  • 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: HK-Sub
Triple: [Hunter-Killer machine, hasVariant, HK-Sub]
Generated description
HK-Sub is an aquatic variant of the Terminator franchise’s Hunter-Killer machines, designed for underwater search-and-destroy operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HK-Sub
Target entity description: HK-Sub is an aquatic variant of the Terminator franchise’s Hunter-Killer machines, designed for underwater search-and-destroy operations.
  • A. HKY
    HKY is the three-letter IATA airport code for Hickory Regional Airport in Hickory, North Carolina, USA.
  • B. Hansu
    Hansu is a central, morally ambiguous Korean businessman in Min Jin Lee’s novel "Pachinko," whose complex relationship with the protagonist’s family drives much of the multigenerational drama.
  • C. HK53
    The HK53 is a compact 5.56×45mm NATO assault rifle developed by Heckler & Koch that combines the roller-delayed blowback system of the G3 family with the size and handling of a submachine gun.
  • D. KMHK
    KMHK is the ICAO airport code for Manhattan Regional Airport, a public airport serving Manhattan, Kansas, in the United States.
  • E. KLHK
    KLHK is the Indonesian government ministry responsible for environmental protection, natural resource management, and forestry policy.
  • 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_69e0b4b2aa788190ae9eb37c1d73b1f1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69f43e0b08190b043f35645b264a0 completed April 20, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a089d3d55a08190b478b4b8f50ff101 completed May 16, 2026, 4:37 p.m.
NEDg Description generation batch_6a089e5816308190979cd7ab78a0c0f6 completed May 16, 2026, 4:42 p.m.
NED2 Entity disambiguation (via description) batch_6a089ecd0f988190afc859a511a18f7b completed May 16, 2026, 4:43 p.m.
Created at: April 16, 2026, 11:36 a.m.