Triple

T15914771
Position Surface form Disambiguated ID Type / Status
Subject Attack of the Cybermen E385940 entity
Predicate featuresCharacter P626 FINISHED
Object Russell
Russell is a supporting character from the classic Doctor Who serial "Attack of the Cybermen," involved in the story’s conflict with the Cybermen.
E1182277 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: Russell | Statement: [Attack of the Cybermen, featuresCharacter, Russell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Russell
Context triple: [Attack of the Cybermen, featuresCharacter, Russell]
  • A. Russell
    Russell is a common English surname most famously associated with legendary Boston Celtics basketball player and civil rights activist Bill Russell.
  • B. Russell
    Russell is the enthusiastic young Wilderness Explorer who befriends elderly widower Carl Fredricksen in Pixar's animated film "Up."
  • C. Russell
    Russell is a sharp-tongued, wisecracking young member of the Junkyard Gang in the animated series "Fat Albert and the Cosby Kids."
  • D. Russell
    Russell is a rural municipality in eastern Ontario, Canada, known for its bilingual (English and French) community and proximity to Ottawa.
  • E. Russell
    Russell is the middle name of Rensselaer Russell Nelson, an American jurist who served as a United States federal judge in the 19th century.
  • 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: Russell
Triple: [Attack of the Cybermen, featuresCharacter, Russell]
Generated description
Russell is a supporting character from the classic Doctor Who serial "Attack of the Cybermen," involved in the story’s conflict with the Cybermen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Russell
Target entity description: Russell is a supporting character from the classic Doctor Who serial "Attack of the Cybermen," involved in the story’s conflict with the Cybermen.
  • A. Russell
    Russell is a sharp-tongued, wisecracking young member of the Junkyard Gang in the animated series "Fat Albert and the Cosby Kids."
  • B. Russell
    Russell is the middle name of British television writer and producer Stephen Russell Davies, better known as Russell T Davies.
  • C. Russell
    Russell is a prominent English surname historically associated with influential aristocratic and political families in Britain.
  • D. Russell
    Russell is a locality in Canberra, Australia, known primarily as a major government and defence precinct housing key national security and administrative offices.
  • E. Russell
    Russell is the enthusiastic young Wilderness Explorer who befriends elderly widower Carl Fredricksen in Pixar's animated film "Up."
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1566216d481908dd6e3acaa26fd45 completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb05b15e8819083b67afa52f46283 completed May 9, 2026, 10:08 p.m.
NEDg Description generation batch_69ffb0cfac808190b32bb25659603fb4 completed May 9, 2026, 10:10 p.m.
NED2 Entity disambiguation (via description) batch_69ffb15b987c8190ae9c96f15fc55b27 completed May 9, 2026, 10:12 p.m.
Created at: April 10, 2026, 4:52 a.m.