Triple

T5143345
Position Surface form Disambiguated ID Type / Status
Subject Terminator 3: Rise of the Machines E116011 entity
Predicate character P662 FINISHED
Object T-850
T-850 is a reprogrammed Terminator cyborg model portrayed by Arnold Schwarzenegger in "Terminator 3: Rise of the Machines," sent back in time to protect John Connor from more advanced machines.
 E498093 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: T-850 | Statement: [Terminator 3: Rise of the Machines, character, T-850]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: T-850
Context triple: [Terminator 3: Rise of the Machines, character, T-850]
  • A. T-25 Universal
    The T-25 Universal is a Brazilian-designed military trainer aircraft widely used for basic flight instruction and pilot training.
  • B. T8
    T8 is a Sydney Trains suburban rail line serving the Airport, Inner South, and South Western suburbs of Sydney, Australia.
  • C. TMB 8000 series
    The TMB 8000 series is a class of electric multiple unit trains used on the Barcelona Metro network for passenger service.
  • D. S85
    S85 is a suburban rail line of the Berlin S-Bahn network serving routes through the German capital and its surrounding areas.
  • E. T-29
    T-29 is a U.S. Air Force military trainer aircraft variant of the Convair 240 series used primarily for navigation and radar training.
  • 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: T-850
Triple: [Terminator 3: Rise of the Machines, character, T-850]
Generated description
T-850 is a reprogrammed Terminator cyborg model portrayed by Arnold Schwarzenegger in "Terminator 3: Rise of the Machines," sent back in time to protect John Connor from more advanced machines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: T-850
Target entity description: T-850 is a reprogrammed Terminator cyborg model portrayed by Arnold Schwarzenegger in "Terminator 3: Rise of the Machines," sent back in time to protect John Connor from more advanced machines.
  • A. T-25 Universal
    The T-25 Universal is a Brazilian-designed military trainer aircraft widely used for basic flight instruction and pilot training.
  • B. T8
    T8 is a Sydney Trains suburban rail line serving the Airport, Inner South, and South Western suburbs of Sydney, Australia.
  • C. TMB 8000 series
    The TMB 8000 series is a class of electric multiple unit trains used on the Barcelona Metro network for passenger service.
  • D. S85
    S85 is a suburban rail line of the Berlin S-Bahn network serving routes through the German capital and its surrounding areas.
  • E. T-29
    T-29 is a U.S. Air Force military trainer aircraft variant of the Convair 240 series used primarily for navigation and radar training.
  • 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_69bd4446c0e08190a7c29dc74976bf03 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7883004881909c763da818d9b6e2 completed March 20, 2026, 4:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69becfec5c108190a3882c25118179a7 completed March 21, 2026, 5:05 p.m.
NEDg Description generation batch_69bed07c9cd081908f8246e24b2f6458 completed March 21, 2026, 5:08 p.m.
NED2 Entity disambiguation (via description) batch_69bed1013fe88190b76855a042226359 completed March 21, 2026, 5:10 p.m.
Created at: March 20, 2026, 1:43 p.m.