Triple

T15636558
Position Surface form Disambiguated ID Type / Status
Subject Jessica Jones E375959 entity
Predicate mainCharacter P1183 FINISHED
Object Trish Walker
Trish Walker is a former child star turned radio host and vigilante, best known as Jessica Jones’s adoptive sister and moral foil in Marvel’s Jessica Jones series.
E1199073 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: Trish Walker | Statement: [Jessica Jones, mainCharacter, Trish Walker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trish Walker
Context triple: [Jessica Jones, mainCharacter, Trish Walker]
  • A. Tricia McAlpin
    Tricia McAlpin is a television producer and writer known for her work as an executive producer on the comedy series "Blunt Talk."
  • B. Trudy Walker
    Trudy Walker is a character in *The Man in the High Castle*, known as the younger sister of protagonist Juliana Crain.
  • C. Lisa Walker
    Lisa Walker is the central protagonist of the television series "Bed of Roses," around whose personal and family dramas the story revolves.
  • D. Melissa Walker
    Melissa Walker is a central character in the sci-fi action film "Timecop," serving as the protagonist's wife whose fate drives the movie's time-traveling plot.
  • E. Tricia Vessey
    Tricia Vessey is an American actress known for her roles in independent films of the late 1990s and early 2000s.
  • 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: Trish Walker
Triple: [Jessica Jones, mainCharacter, Trish Walker]
Generated description
Trish Walker is a former child star turned radio host and vigilante, best known as Jessica Jones’s adoptive sister and moral foil in Marvel’s Jessica Jones series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Trish Walker
Target entity description: Trish Walker is a former child star turned radio host and vigilante, best known as Jessica Jones’s adoptive sister and moral foil in Marvel’s Jessica Jones series.
  • A. Tricia McAlpin
    Tricia McAlpin is a television producer and writer known for her work as an executive producer on the comedy series "Blunt Talk."
  • B. Trudy Walker
    Trudy Walker is a character in *The Man in the High Castle*, known as the younger sister of protagonist Juliana Crain.
  • C. Lisa Walker
    Lisa Walker is the central protagonist of the television series "Bed of Roses," around whose personal and family dramas the story revolves.
  • D. Melissa Walker
    Melissa Walker is a central character in the sci-fi action film "Timecop," serving as the protagonist's wife whose fate drives the movie's time-traveling plot.
  • E. Tricia Vessey
    Tricia Vessey is an American actress known for her roles in independent films of the late 1990s and early 2000s.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eba51f08190ac5d9de7fc89405a completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffee4f84c81908b2c7e216ef159e0 completed May 10, 2026, 3:43 a.m.
NEDg Description generation batch_6a0002419cec81909e3cec70968b65a4 completed May 10, 2026, 3:57 a.m.
NED2 Entity disambiguation (via description) batch_6a0002ad960c81909c308a12da9b65d6 completed May 10, 2026, 3:59 a.m.
Created at: April 10, 2026, 4:14 a.m.