Triple

T18826258
Position Surface form Disambiguated ID Type / Status
Subject The Rink E460393 entity
Predicate castMember P1668 FINISHED
Object Tom Wood
Tom Wood is an actor known for his role in the film "The Rink."
 E1344755 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: Tom Wood | Statement: [The Rink, castMember, Tom Wood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tom Wood
Context triple: [The Rink, castMember, Tom Wood]
  • A. Harry Woods
    Harry Woods was an American character actor best known for his prolific portrayals of villains in numerous Hollywood films from the silent era through the 1950s.
  • B. Howard Wood
    Howard Wood is an American businessman best known as a co-founder and early leader of the telecommunications and cable company Charter Communications.
  • C. Tony Woodley
    Tony Woodley is a British trade union leader best known for heading one of the UK’s largest unions and playing a prominent role in labor and political campaigns.
  • D. John Wood
    John Wood was a British actor active in the early 20th century who appeared in films such as the 1935 historical drama "The Last Days of Pompeii."
  • E. John Wood
    John Wood was a British character actor known for his distinguished stage and screen career, including roles in films such as "Jumpin' Jack Flash" and "WarGames."
  • 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: Tom Wood
Triple: [The Rink, castMember, Tom Wood]
Generated description
Tom Wood is an actor known for his role in the film "The Rink."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tom Wood
Target entity description: Tom Wood is an actor known for his role in the film "The Rink."
  • A. Harry Woods
    Harry Woods was an American character actor best known for his prolific portrayals of villains in numerous Hollywood films from the silent era through the 1950s.
  • B. Howard Wood
    Howard Wood is an American businessman best known as a co-founder and early leader of the telecommunications and cable company Charter Communications.
  • C. Tony Woodley
    Tony Woodley is a British trade union leader best known for heading one of the UK’s largest unions and playing a prominent role in labor and political campaigns.
  • D. John Wood
    John Wood was a British character actor known for his distinguished stage and screen career, including roles in films such as "Jumpin' Jack Flash" and "WarGames."
  • E. John Wood
    John Wood was a British actor active in the early 20th century who appeared in films such as the 1935 historical drama "The Last Days of Pompeii."
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6bec7b08190b040ec8b3693f037 completed April 20, 2026, 4:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a055bd068588190bc34b99796e1a3e1 completed May 14, 2026, 5:21 a.m.
NEDg Description generation batch_6a0560c0ef4c819082b51fd8cee8c738 completed May 14, 2026, 5:42 a.m.
NED2 Entity disambiguation (via description) batch_6a05615a8a7481908ec4c6f9835ca616 completed May 14, 2026, 5:44 a.m.
Created at: April 10, 2026, 11:56 a.m.