Triple

T1545388
Position Surface form Disambiguated ID Type / Status
Subject Sleepless in Seattle E32965 entity
Predicate writer P1360 FINISHED
Object Jeff Arch
Jeff Arch is an American screenwriter best known for co-writing the hit romantic comedy film "Sleepless in Seattle."
E178294 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: Jeff Arch | Statement: [Sleepless in Seattle, writer, Jeff Arch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeff Arch
Context triple: [Sleepless in Seattle, writer, Jeff Arch]
  • A. Raymond Gardner
    Raymond Gardner was the brother of famed American actress Ava Gardner, a member of the Gardner family from rural North Carolina.
  • B. Tom Fleming
    Tom Fleming is a name shared by several notable individuals, including an American long-distance runner and a Scottish actor and comedian.
  • C. Richard Johns
    Richard Johns is a senior Royal Air Force officer who served as Air Officer Commanding-in-Chief of Fighter Command.
  • D. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • E. Vincent Winter
    Vincent Winter was a Scottish child actor who gained prominence in the 1950s and 1960s, later working behind the scenes in film production.
  • 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: Jeff Arch
Triple: [Sleepless in Seattle, writer, Jeff Arch]
Generated description
Jeff Arch is an American screenwriter best known for co-writing the hit romantic comedy film "Sleepless in Seattle."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jeff Arch
Target entity description: Jeff Arch is an American screenwriter best known for co-writing the hit romantic comedy film "Sleepless in Seattle."
  • A. Raymond Gardner
    Raymond Gardner was the brother of famed American actress Ava Gardner, a member of the Gardner family from rural North Carolina.
  • B. Tom Fleming
    Tom Fleming is a name shared by several notable individuals, including an American long-distance runner and a Scottish actor and comedian.
  • C. Richard Johns
    Richard Johns is a senior Royal Air Force officer who served as Air Officer Commanding-in-Chief of Fighter Command.
  • D. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • E. Vincent Winter
    Vincent Winter was a Scottish child actor who gained prominence in the 1950s and 1960s, later working behind the scenes in film production.
  • 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_69a885ed29088190a3c2d5a3d100c16e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90842a4788190a812b48987503624 completed March 5, 2026, 4:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad4018f4c08190ad1994389b4e244c completed March 8, 2026, 9:23 a.m.
NEDg Description generation batch_69ad40b363bc819098a6d80f07cc80ce completed March 8, 2026, 9:26 a.m.
NED2 Entity disambiguation (via description) batch_69ad40fee2348190a048e97bfd747267 completed March 8, 2026, 9:27 a.m.
Created at: March 4, 2026, 7:26 p.m.