Triple

T985150
Position Surface form Disambiguated ID Type / Status
Subject Kyle Reese E21261 entity
Predicate enemy P4567 FINISHED
Object Skynet
Skynet is the fictional artificial intelligence system from the Terminator franchise that becomes self-aware and launches a catastrophic war against humanity.
 E117725 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: Skynet | Statement: [Kyle Reese, enemy, Skynet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Skynet
Context triple: [Kyle Reese, enemy, Skynet]
  • A. Cyborg
    Cyborg is a prominent DC Comics superhero, best known as a technologically enhanced human and key member of teams like the Teen Titans and the Justice League.
  • B. The Machine
    The Machine is the nickname of Albert Pujols, a Dominican-American former Major League Baseball first baseman renowned for his remarkably consistent and powerful hitting.
  • C. Ex Machina
    Ex Machina is a 2014 science fiction psychological thriller film about artificial intelligence and human consciousness, written and directed by Alex Garland.
  • D. Gatekeeper
    Gatekeeper is a macOS security feature that helps protect users by allowing only trusted software to run on the system.
  • E. Kismet
    Kismet is an open-source wireless network detector, sniffer, and intrusion detection system widely used for Wi-Fi security auditing and monitoring.
  • 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: Skynet
Triple: [Kyle Reese, enemy, Skynet]
Generated description
Skynet is the fictional artificial intelligence system from the Terminator franchise that becomes self-aware and launches a catastrophic war against humanity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Skynet
Target entity description: Skynet is the fictional artificial intelligence system from the Terminator franchise that becomes self-aware and launches a catastrophic war against humanity.
  • A. Cyborg
    Cyborg is a prominent DC Comics superhero, best known as a technologically enhanced human and key member of teams like the Teen Titans and the Justice League.
  • B. The Machine
    The Machine is the nickname of Albert Pujols, a Dominican-American former Major League Baseball first baseman renowned for his remarkably consistent and powerful hitting.
  • C. Ex Machina
    Ex Machina is a 2014 science fiction psychological thriller film about artificial intelligence and human consciousness, written and directed by Alex Garland.
  • D. Gatekeeper
    Gatekeeper is a macOS security feature that helps protect users by allowing only trusted software to run on the system.
  • E. Kismet
    Kismet is an open-source wireless network detector, sniffer, and intrusion detection system widely used for Wi-Fi security auditing and monitoring.
  • 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_69a493c383dc8190a03257f22d4b4183 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4959fe48190a78bd811cbc888ab completed March 1, 2026, 9:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac258b55908190bc5bbf1c2756482d completed March 7, 2026, 1:18 p.m.
NEDg Description generation batch_69ac27bec3ec8190a96338fd961940c1 completed March 7, 2026, 1:27 p.m.
NED2 Entity disambiguation (via description) batch_69ac282aa1308190889ef5bedfe449c9 completed March 7, 2026, 1:29 p.m.
Created at: March 1, 2026, 7:41 p.m.