Triple

T11618338
Position Surface form Disambiguated ID Type / Status
Subject Ghostwire: Tokyo E275565 entity
Predicate notableCharacter P1481 FINISHED
Object KK
KK is a key spirit detective and mentor figure in the action-adventure game Ghostwire: Tokyo, guiding the protagonist with his supernatural expertise.
 E937142 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: KK | Statement: [Ghostwire: Tokyo, notableCharacter, KK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KK
Context triple: [Ghostwire: Tokyo, notableCharacter, KK]
  • A. KK
    KK is the commonly used abbreviation for Kota Kinabalu, the capital city of Sabah in Malaysian Borneo known for its coastal setting and proximity to Mount Kinabalu.
  • B. KK
    KK is the vehicle registration code used on license plates for the Kežmarok district in Slovakia.
  • C. KC
    KC is a common shorthand nickname for Kansas City, Missouri, a major Midwestern U.S. city known for its jazz heritage, barbecue, and sports teams.
  • D. KC
    KC is the commonly used abbreviation for The Kennel Club, the United Kingdom’s official kennel club and governing body for dog breeding, shows, and related canine activities.
  • E. KC
    KC is the vehicle registration code used on license plates for the district of Kronach in Upper Franconia, Germany.
  • 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: KK
Triple: [Ghostwire: Tokyo, notableCharacter, KK]
Generated description
KK is a key spirit detective and mentor figure in the action-adventure game Ghostwire: Tokyo, guiding the protagonist with his supernatural expertise.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KK
Target entity description: KK is a key spirit detective and mentor figure in the action-adventure game Ghostwire: Tokyo, guiding the protagonist with his supernatural expertise.
  • A. KK
    KK is the commonly used abbreviation for Kota Kinabalu, the capital city of Sabah in Malaysian Borneo known for its coastal setting and proximity to Mount Kinabalu.
  • B. KK
    KK is the vehicle registration code used on license plates for the Kežmarok district in Slovakia.
  • C. KC
    KC is a common shorthand nickname for Kansas City, Missouri, a major Midwestern U.S. city known for its jazz heritage, barbecue, and sports teams.
  • D. KC
    KC is the vehicle registration code used on license plates for the district of Kronach in Upper Franconia, Germany.
  • E. KC
    KC is the commonly used abbreviation for The Kennel Club, the United Kingdom’s official kennel club and governing body for dog breeding, shows, and related canine activities.
  • 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_69d6aaf84b548190ac072e4fb89ae18f completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a047758081908191c1d564409d9a completed April 10, 2026, 7:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69ee873ee6888190ab6e87ed0f4ae731 completed April 26, 2026, 9:44 p.m.
NEDg Description generation batch_69ee9cf692e08190b135de0bd7f96274 completed April 26, 2026, 11:17 p.m.
NED2 Entity disambiguation (via description) batch_69eecd715b448190b738479b7c1379a2 completed April 27, 2026, 2:44 a.m.
Created at: April 8, 2026, 9:38 p.m.