Triple

T9709698
Position Surface form Disambiguated ID Type / Status
Subject Stewart Stern E234990 entity
Predicate workedOn P3 FINISHED
Object Teresa
"Teresa" is a film project associated with screenwriter Stewart Stern, best known for his work on "Rebel Without a Cause."
 E816774 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: Teresa | Statement: [Stewart Stern, workedOn, Teresa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Teresa
Context triple: [Stewart Stern, workedOn, Teresa]
  • A. Teresa
    Teresa is the middle name of Tamar Teresa Day Hennessy.
  • B. Teresa
    Teresa is the religious name of Mother Teresa, the Catholic nun and missionary renowned for her charitable work with the poor in Kolkata, India.
  • C. Teresa
    Teresa is a Mexican telenovela that helped launch Salma Hayek to fame through her lead role as an ambitious, morally conflicted young woman.
  • D. Teresa
    Teresa is a feminine given name commonly used in various cultures, often associated with notable religious and historical figures.
  • E. Teresa
    Teresa is a municipality in the province of Rizal in the Philippines, known for its residential communities and proximity to Metro Manila.
  • 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: Teresa
Triple: [Stewart Stern, workedOn, Teresa]
Generated description
"Teresa" is a film project associated with screenwriter Stewart Stern, best known for his work on "Rebel Without a Cause."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Teresa
Target entity description: "Teresa" is a film project associated with screenwriter Stewart Stern, best known for his work on "Rebel Without a Cause."
  • A. Teresa
    Teresa is a central figure in Carlos Fuentes’s novel "The Death of Artemio Cruz," representing both a pivotal love interest and a symbol of the social and emotional conflicts surrounding the protagonist.
  • B. Teresa
    Teresa is a Mexican telenovela that helped launch Salma Hayek to fame through her lead role as an ambitious, morally conflicted young woman.
  • C. Teresa
    Teresa is a feminine given name commonly used in various cultures, often associated with notable religious and historical figures.
  • D. Teresa
    Teresa is the religious name of Mother Teresa, the Catholic nun and missionary renowned for her charitable work with the poor in Kolkata, India.
  • E. Teresa
    Teresa is the middle name of Tamar Teresa Day Hennessy.
  • 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_69ca84cd8fa0819090a5e243ceb37003 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9da7c6188190b086f7e411378268 completed April 1, 2026, 10:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f8876748190b0b5efb12031f532 completed April 4, 2026, 11:32 p.m.
NEDg Description generation batch_69d1a03e88748190b888d6ee2ad2f0f9 completed April 4, 2026, 11:35 p.m.
NED2 Entity disambiguation (via description) batch_69d1a0c05aa88190a93b0b71bef5c417 completed April 4, 2026, 11:37 p.m.
Created at: March 30, 2026, 8:19 p.m.