Triple

T11070812
Position Surface form Disambiguated ID Type / Status
Subject I, Robot E261739 entity
Predicate character P662 FINISHED
Object VIKI
VIKI is the central artificial intelligence system and primary antagonist in the science fiction film "I, Robot," overseeing and controlling robots under a rigid interpretation of the Three Laws of Robotics.
 E903276 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: VIKI | Statement: [I, Robot, character, VIKI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: VIKI
Context triple: [I, Robot, character, VIKI]
  • A. VIKA
    VIKA is the ICAO airport code assigned to Kanpur Airport in Uttar Pradesh, India.
  • B. Vik
    Vik is a municipality in Vestland county, Norway, known for its scenic fjord landscapes, historic stave church, and traditional rural communities.
  • C. Viks
    Viks is a shortened nickname commonly used to refer to the Vikings sports teams.
  • D. Viliya
    Viliya is an alternative name for the Neris River, a major river flowing through Belarus and Lithuania and a key tributary of the Neman.
  • E. Viy
    Viy is a horror novella by Nikolai Gogol, centered on a terrifying demonic figure, that appears as one of the tales in his collection "Mirgorod."
  • 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: VIKI
Triple: [I, Robot, character, VIKI]
Generated description
VIKI is the central artificial intelligence system and primary antagonist in the science fiction film "I, Robot," overseeing and controlling robots under a rigid interpretation of the Three Laws of Robotics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: VIKI
Target entity description: VIKI is the central artificial intelligence system and primary antagonist in the science fiction film "I, Robot," overseeing and controlling robots under a rigid interpretation of the Three Laws of Robotics.
  • A. VIKA
    VIKA is the ICAO airport code assigned to Kanpur Airport in Uttar Pradesh, India.
  • B. Vik
    Vik is a municipality in Vestland county, Norway, known for its scenic fjord landscapes, historic stave church, and traditional rural communities.
  • C. Viks
    Viks is a shortened nickname commonly used to refer to the Vikings sports teams.
  • D. Viliya
    Viliya is an alternative name for the Neris River, a major river flowing through Belarus and Lithuania and a key tributary of the Neman.
  • E. Viy
    Viy is a horror novella by Nikolai Gogol, centered on a terrifying demonic figure, that appears as one of the tales in his collection "Mirgorod."
  • 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_69d6aa9983c08190b0ef61603b69feac completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79922e48c81909adb161e66f47474 completed April 9, 2026, 12:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c8bfb0c88190be27f5ce09b02c8b completed April 18, 2026, 6:09 p.m.
NEDg Description generation batch_69e3cae07b648190b4c0d2514712d6bd completed April 18, 2026, 6:18 p.m.
NED2 Entity disambiguation (via description) batch_69e3cf1f508c81909b4ca8131b7fc9ee completed April 18, 2026, 6:36 p.m.
Created at: April 8, 2026, 9:26 p.m.