Triple

T15914774
Position Surface form Disambiguated ID Type / Status
Subject Attack of the Cybermen E385940 entity
Predicate featuresCharacter P626 FINISHED
Object Varne
Varne is a minor character from the classic Doctor Who serial "Attack of the Cybermen," appearing as part of the story’s supporting cast.
 E1182279 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: Varne | Statement: [Attack of the Cybermen, featuresCharacter, Varne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Varne
Context triple: [Attack of the Cybermen, featuresCharacter, Varne]
  • A. Varna
    Varna is a major Bulgarian city on the Black Sea coast known as an important economic, cultural, and maritime center.
  • B. Varde
    Varde is a Danish town known for its historic center and location near the North Sea coast in the Region of Southern Denmark.
  • C. Sandanski
    Sandanski is a town in southwestern Bulgaria known as a spa and climatic resort in the Struma River valley near the Greek border.
  • D. Varėna
    Varėna is a town in southeastern Lithuania known as the birthplace of the renowned composer and painter Mikalojus Konstantinas Čiurlionis.
  • E. Grenaa
    Grenaa is a coastal town in eastern Jutland, Denmark, known for its ferry connections to the island of Anholt and its role as a regional commercial and educational center.
  • 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: Varne
Triple: [Attack of the Cybermen, featuresCharacter, Varne]
Generated description
Varne is a minor character from the classic Doctor Who serial "Attack of the Cybermen," appearing as part of the story’s supporting cast.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Varne
Target entity description: Varne is a minor character from the classic Doctor Who serial "Attack of the Cybermen," appearing as part of the story’s supporting cast.
  • A. Varna
    Varna is a major Bulgarian city on the Black Sea coast known as an important economic, cultural, and maritime center.
  • B. Varde
    Varde is a Danish town known for its historic center and location near the North Sea coast in the Region of Southern Denmark.
  • C. Sandanski
    Sandanski is a town in southwestern Bulgaria known as a spa and climatic resort in the Struma River valley near the Greek border.
  • D. Varėna
    Varėna is a town in southeastern Lithuania known as the birthplace of the renowned composer and painter Mikalojus Konstantinas Čiurlionis.
  • E. Grenaa
    Grenaa is a coastal town in eastern Jutland, Denmark, known for its ferry connections to the island of Anholt and its role as a regional commercial and educational center.
  • 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.