Triple

T22797969
Position Surface form Disambiguated ID Type / Status
Subject Pretty Little Liars E564301 entity
Predicate authorOfSourceMaterial P2806 FINISHED
Object Sara Shepard NE NERFINISHED

How this triple was built (2 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: Sara Shepard | Statement: [Pretty Little Liars, authorOfSourceMaterial, Sara Shepard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Shepard
Context triple: [Pretty Little Liars, authorOfSourceMaterial, Sara Shepard]
  • A. Sara Shepard chosen
    Sara Shepard is an American author best known for writing the young adult mystery series "Pretty Little Liars," which inspired the popular television adaptation.
  • B. Sarah Shephard
    Sarah Shephard is a fictional character from the television series "Lost," known as Jack Shephard’s ex-wife.
  • C. Alexandra Bracken
    Alexandra Bracken is an American author best known for her young adult science fiction and fantasy novels, particularly the popular dystopian series that began with *The Darkest Minds*.
  • D. Richelle Mead
    Richelle Mead is an American fantasy author best known for her popular young adult and urban fantasy series, including the Vampire Academy and Bloodlines novels.
  • E. Maureen Johnson
    Maureen Johnson is a flamboyant, performance-artist character in the musical "Rent," known for her dramatic personality and complex romantic relationships.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cda76448190891c5190e1d75ae0 completed April 29, 2026, 3:36 a.m.
Created at: April 17, 2026, 3:30 p.m.