Triple

T30856663
Position Surface form Disambiguated ID Type / Status
Subject Welcome Back, Kotter E785941 entity
Predicate starring P1507 FINISHED
Object Robert Hegyes
Robert Hegyes was an American actor best known for playing Juan Epstein, one of the Sweathogs, on the 1970s sitcom "Welcome Back, Kotter."
E2007698 NE FINISHED

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: Robert Hegyes | Statement: [Welcome Back, Kotter, starring, Robert Hegyes]
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: Robert Hegyes
Triple: [Welcome Back, Kotter, starring, Robert Hegyes]
Generated description
Robert Hegyes was an American actor best known for playing Juan Epstein, one of the Sweathogs, on the 1970s sitcom "Welcome Back, Kotter."

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_69f224b91c14819084e764832fe67a57 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f691a5995081909ec37fc167c286d0 completed May 3, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a34665207a081908152ee52b113938a completed June 18, 2026, 9:42 p.m.
NEDg Description generation batch_6a346777b13481908d5d05cb281e940d completed June 18, 2026, 9:47 p.m.
NED2 Entity disambiguation (via description) batch_6a3468279dbc8190b5efcecd6f4aa23c completed June 18, 2026, 9:50 p.m.
Created at: April 29, 2026, 8:46 p.m.