Triple

T13420618
Position Surface form Disambiguated ID Type / Status
Subject Shepherd in a Sheepskin Vest E313338 entity
Predicate hasPart P35 FINISHED
Object “747”
“747” is a track from Bill Callahan’s introspective folk album "Shepherd in a Sheepskin Vest."
 E1038953 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: “747” | Statement: [Shepherd in a Sheepskin Vest, hasPart, “747”]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: “747”
Context triple: [Shepherd in a Sheepskin Vest, hasPart, “747”]
  • A. Boeing 747
    The Boeing 747 is a wide-body, long-range commercial airliner famous for its distinctive hump-backed upper deck and for revolutionizing mass international air travel as one of the first jumbo jets.
  • B. STM 747 bus
    The STM 747 bus is an express public transit route in Montreal that connects the city’s downtown core with Montréal–Trudeau International Airport.
  • C. Boeing 777
    The Boeing 777 is a long-range, wide-body twin-engine jet airliner widely used by airlines around the world for international passenger flights.
  • D. Xian MA60
    The Xian MA60 is a Chinese-built twin-turboprop regional airliner designed for short- to medium-haul passenger services.
  • E. B7700
    B7700 is a model of Burroughs large mainframe computer system designed for high-performance business and scientific computing.
  • 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: “747”
Triple: [Shepherd in a Sheepskin Vest, hasPart, “747”]
Generated description
“747” is a track from Bill Callahan’s introspective folk album "Shepherd in a Sheepskin Vest."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: “747”
Target entity description: “747” is a track from Bill Callahan’s introspective folk album "Shepherd in a Sheepskin Vest."
  • A. Boeing 747
    The Boeing 747 is a wide-body, long-range commercial airliner famous for its distinctive hump-backed upper deck and for revolutionizing mass international air travel as one of the first jumbo jets.
  • B. STM 747 bus
    The STM 747 bus is an express public transit route in Montreal that connects the city’s downtown core with Montréal–Trudeau International Airport.
  • C. Boeing 777
    The Boeing 777 is a long-range, wide-body twin-engine jet airliner widely used by airlines around the world for international passenger flights.
  • D. Xian MA60
    The Xian MA60 is a Chinese-built twin-turboprop regional airliner designed for short- to medium-haul passenger services.
  • E. B7700
    B7700 is a model of Burroughs large mainframe computer system designed for high-performance business and scientific computing.
  • 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaeb98e808190948013e8f24779c6 completed April 12, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7308493e481909da52f8bbcc0bd6b completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f73195e4d88190ad356d0e3e18d34f completed May 3, 2026, 11:29 a.m.
NED2 Entity disambiguation (via description) batch_69f73220ffc08190bfb1b89757efd606 completed May 3, 2026, 11:31 a.m.
Created at: April 9, 2026, 9:39 p.m.