Triple

T21423521
Position Surface form Disambiguated ID Type / Status
Subject Z-machine E528495 entity
Predicate executes P9410 FINISHED
Object Z-code
Z-code is the compact, platform-independent bytecode format used by Infocom and related interactive fiction systems to represent and run text adventure games on the Z-machine.
 E1483018 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: Z-code | Statement: [Z-machine, executes, Z-code]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Z-code
Context triple: [Z-machine, executes, Z-code]
  • A. ZCO
    ZCO is the IATA airport code for La Araucanía International Airport, which serves the Temuco region in southern Chile.
  • B. ZC
    ZC is the governing body responsible for overseeing and developing the sport of cricket in Zimbabwe.
  • C. LZA
    LZA is the regional vehicle registration code assigned to motor vehicles registered in the city of Zamość in Poland.
  • D. ZF
    ZF is the standard axiomatic framework for set theory that underpins much of modern mathematics.
  • E. ZF
    ZF is a German automotive supplier and technology company known for producing driveline and chassis components as well as active and passive safety systems.
  • 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: Z-code
Triple: [Z-machine, executes, Z-code]
Generated description
Z-code is the compact, platform-independent bytecode format used by Infocom and related interactive fiction systems to represent and run text adventure games on the Z-machine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Z-code
Target entity description: Z-code is the compact, platform-independent bytecode format used by Infocom and related interactive fiction systems to represent and run text adventure games on the Z-machine.
  • A. ZCO
    ZCO is the IATA airport code for La Araucanía International Airport, which serves the Temuco region in southern Chile.
  • B. ZC
    ZC is the governing body responsible for overseeing and developing the sport of cricket in Zimbabwe.
  • C. LZA
    LZA is the regional vehicle registration code assigned to motor vehicles registered in the city of Zamość in Poland.
  • D. ZF
    ZF is the standard axiomatic framework for set theory that underpins much of modern mathematics.
  • E. ZF
    ZF is a German automotive supplier and technology company known for producing driveline and chassis components as well as active and passive safety systems.
  • 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_69e0c455f3688190810bc96365791b0f completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee8139ce848190b812d6d07f1bdef8 completed April 26, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a09c2a5a6488190a753c0359d2702f3 completed May 17, 2026, 1:29 p.m.
NEDg Description generation batch_6a09c31840648190bde2d313dd0f02e4 completed May 17, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_6a09c361f5b481908f8c5215381a7c98 completed May 17, 2026, 1:32 p.m.
Created at: April 16, 2026, 5:48 p.m.