Triple

T23389018
Position Surface form Disambiguated ID Type / Status
Subject Harvard Man (film) E593960 entity
Predicate characterPlayedBy P1507 FINISHED
Object Teddy – Eric Stoltz
Teddy is a character portrayed by Eric Stoltz in the dark comedy crime film "Harvard Man."
E1582301 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: Teddy – Eric Stoltz | Statement: [Harvard Man (film), characterPlayedBy, Teddy – Eric Stoltz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teddy – Eric Stoltz
Context triple: [Harvard Man (film), characterPlayedBy, Teddy – Eric Stoltz]
  • A. Teddy
    Teddy is the given name of Teddy Reig, an American jazz record producer and A&R man known for his work with prominent bebop and swing musicians.
  • B. Teddy
    Teddy is a character in Louisa May Alcott’s novel "Jo’s Boys," part of the continuation of the March family saga begun in "Little Women."
  • C. Teddy
    Teddy is the nickname of Teddy Kollek, the long-serving and influential former mayor of Jerusalem.
  • D. Teddy
    Teddy is the young English boy in Rudyard Kipling’s story “Rikki-Tikki-Tavi,” whose life is saved from deadly cobras by the brave mongoose.
  • E. Teddy
    Teddy is a short story by J.D. Salinger that follows a spiritually precocious child whose philosophical insights unsettle the adults around him.
  • 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: Teddy – Eric Stoltz
Triple: [Harvard Man (film), characterPlayedBy, Teddy – Eric Stoltz]
Generated description
Teddy is a character portrayed by Eric Stoltz in the dark comedy crime film "Harvard Man."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Teddy – Eric Stoltz
Target entity description: Teddy is a character portrayed by Eric Stoltz in the dark comedy crime film "Harvard Man."
  • A. Teddy
    Teddy is a character in Louisa May Alcott’s novel "Jo’s Boys," part of the continuation of the March family saga begun in "Little Women."
  • B. Teddy
    Teddy is the given name of Teddy Reig, an American jazz record producer and A&R man known for his work with prominent bebop and swing musicians.
  • C. Teddy
    Teddy is Mr. Bean’s beloved brown teddy bear, a silent yet expressive companion that often serves as his confidant and playmate in the comedy series.
  • D. Teddy
    Teddy is a recurring character on the animated TV show "Bob's Burgers," known as the Belcher family's loyal but somewhat bumbling handyman and regular customer.
  • E. Teddy
    Teddy is the nickname of Teddy Kollek, the long-serving and influential former mayor of Jerusalem.
  • 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_69e25d2754fc819085deea939bde60ab completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a49a7c14819082aab826715976c5 completed April 29, 2026, 6:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c5de999488190be021920241b7f25 completed May 19, 2026, 12:56 p.m.
NEDg Description generation batch_6a0c5e7eb7b481908b3cece1823cf785 completed May 19, 2026, 12:58 p.m.
NED2 Entity disambiguation (via description) batch_6a0c5eef81e48190b62da26fb8d65223 completed May 19, 2026, 1 p.m.
Created at: April 17, 2026, 5:35 p.m.