Triple

T36114351
Position Surface form Disambiguated ID Type / Status
Subject Broadway production of Rodgers & Hammerstein's Cinderella E1044578 entity
Predicate originalBroadwayMadamePortrayedBy P4737 FINISHED
Object Harriet Harris
Harriet Harris is a Tony Award–winning American actress known for her sharp comic timing and distinctive character roles on Broadway, television, and film.
 E2238434 NE FINISHED

How this triple was built (3 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: Harriet Harris | Statement: [Broadway production of Rodgers & Hammerstein's Cinderella, originalBroadwayMadamePortrayedBy, Harriet Harris]
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: Harriet Harris
Triple: [Broadway production of Rodgers & Hammerstein's Cinderella, originalBroadwayMadamePortrayedBy, Harriet Harris]
Generated description
Harriet Harris is a Tony Award–winning American actress known for her sharp comic timing and distinctive character roles on Broadway, television, and film.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: originalBroadwayMadamePortrayedBy
Context triple: [Broadway production of Rodgers & Hammerstein's Cinderella, originalBroadwayMadamePortrayedBy, Harriet Harris]
  • A. portrayedInBroadwayProductionBy
    Indicates that an entity was depicted or performed in a Broadway stage production by a specified person or group.
  • B. originalBroadwayStar chosen
    Indicates that the subject was a member of the original Broadway cast in the specified role or production.
  • C. portrayedInOriginalOffBroadwayProductionBy
    Indicates that an entity was depicted or played by a particular performer in the original Off-Broadway production of a work.
  • D. originalBroadwayCoStar
    Indicates that two performers appeared together as co-stars in the original Broadway production of the same show.
  • E. appearedInBroadwayProduction
    Indicates that an entity participated as part of a Broadway stage production of another work or show.
  • F. None of above.

Provenance (6 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_69f76e344a4c8190af3858c6d78ba88f completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a037c8d06cc8190ab6a5e18d9d2571e completed May 12, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a40cd9d361481909b1f5da612e9359a completed June 28, 2026, 7:30 a.m.
NEDg Description generation batch_6a40ce3d01a08190952db5afe4d11324 completed June 28, 2026, 7:33 a.m.
NED2 Entity disambiguation (via description) batch_6a40cec32e4c819095b877087cd7fcdd completed June 28, 2026, 7:35 a.m.
PD Predicate disambiguation batch_6a037a0895b48190acdd88dc10db7be7 completed May 12, 2026, 7:05 p.m.
Created at: May 3, 2026, 4:08 p.m.