Triple

T19469928
Position Surface form Disambiguated ID Type / Status
Subject Sweet Tooth E487093 entity
Predicate hasCharacter P2308 FINISHED
Object Tom Haley
Tom Haley is a character in the post-apocalyptic comic and TV series "Sweet Tooth," which follows human-animal hybrid children surviving in a devastated world.
 E1378876 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 Haley | Statement: [Sweet Tooth, hasCharacter, Tom Haley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tom Haley
Context triple: [Sweet Tooth, hasCharacter, Tom Haley]
  • A. Ray Roberts
    Ray Roberts was a Texas politician whose public service and regional influence led to a major state reservoir, Ray Roberts Lake, being named in his honor.
  • B. Jimmy Nalls
    Jimmy Nalls was an American guitarist best known for his work with the Southern rock band Sea Level and his contributions to the broader Southern rock scene.
  • C. Del Moore
    Del Moore was an American character actor and comedian best known for his supporting roles in mid-20th-century film and television comedies.
  • D. Thomas Lumpkins
    Thomas Lumpkins is a songwriter best known for co-writing Janet Jackson’s single "No Sleeep."
  • E. Lamar Johnson
    Lamar Johnson is a Canadian actor known for roles in film and television, including his appearance in HBO's adaptation of "The Last of Us."
  • 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 Haley
Triple: [Sweet Tooth, hasCharacter, Tom Haley]
Generated description
Tom Haley is a character in the post-apocalyptic comic and TV series "Sweet Tooth," which follows human-animal hybrid children surviving in a devastated world.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tom Haley
Target entity description: Tom Haley is a character in the post-apocalyptic comic and TV series "Sweet Tooth," which follows human-animal hybrid children surviving in a devastated world.
  • A. Ray Roberts
    Ray Roberts was a Texas politician whose public service and regional influence led to a major state reservoir, Ray Roberts Lake, being named in his honor.
  • B. Jimmy Nalls
    Jimmy Nalls was an American guitarist best known for his work with the Southern rock band Sea Level and his contributions to the broader Southern rock scene.
  • C. Del Moore
    Del Moore was an American character actor and comedian best known for his supporting roles in mid-20th-century film and television comedies.
  • D. Thomas Lumpkins
    Thomas Lumpkins is a songwriter best known for co-writing Janet Jackson’s single "No Sleeep."
  • E. Lamar Johnson
    Lamar Johnson is a Canadian actor known for roles in film and television, including his appearance in HBO's adaptation of "The Last of Us."
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633e6fd988190b79be580b65746fe completed April 20, 2026, 2:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07404dfcb881909ed1a7ac20b6461e completed May 15, 2026, 3:48 p.m.
NEDg Description generation batch_6a0740ff37fc81908e68db633223fb9c completed May 15, 2026, 3:51 p.m.
NED2 Entity disambiguation (via description) batch_6a07424880e08190a582da18e3a6af19 completed May 15, 2026, 3:56 p.m.
Created at: April 10, 2026, 1:39 p.m.