Triple

T16611294
Position Surface form Disambiguated ID Type / Status
Subject Parnall Correctional Facility E403574 entity
Predicate alsoKnownAs P39 FINISHED
Object Parnall
Parnall is a Michigan state prison facility that houses adult male inmates and is part of the Jackson-area prison complex.
E1222976 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: Parnall | Statement: [Parnall Correctional Facility, alsoKnownAs, Parnall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parnall
Context triple: [Parnall Correctional Facility, alsoKnownAs, Parnall]
  • A. Privett
    Privett is a small rural village in the East Hampshire district of Hampshire, England, known for its historic church and countryside setting.
  • B. Bicknoller
    Bicknoller is a small rural village in Somerset, England, situated on the slopes of the Quantock Hills and known for its historic church and traditional countryside character.
  • C. Minstead
    Minstead is a small village in Hampshire, England, best known as the burial place of Sir Arthur Conan Doyle.
  • D. Marling
    Marling is an English surname historically associated with British nobility and public service.
  • E. Coryton
    Coryton is a suburban area and railway terminus in Cardiff, Wales, served by local commuter trains.
  • 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: Parnall
Triple: [Parnall Correctional Facility, alsoKnownAs, Parnall]
Generated description
Parnall is a Michigan state prison facility that houses adult male inmates and is part of the Jackson-area prison complex.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Parnall
Target entity description: Parnall is a Michigan state prison facility that houses adult male inmates and is part of the Jackson-area prison complex.
  • A. Privett
    Privett is a small rural village in the East Hampshire district of Hampshire, England, known for its historic church and countryside setting.
  • B. Bicknoller
    Bicknoller is a small rural village in Somerset, England, situated on the slopes of the Quantock Hills and known for its historic church and traditional countryside character.
  • C. Minstead
    Minstead is a small village in Hampshire, England, best known as the burial place of Sir Arthur Conan Doyle.
  • D. Marling
    Marling is an English surname historically associated with British nobility and public service.
  • E. Coryton
    Coryton is a suburban area and railway terminus in Cardiff, Wales, served by local commuter trains.
  • 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_69d883880d0c81908b5fcd454e767b60 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e36096356c819092815d64db041793 completed April 18, 2026, 10:44 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0075aca5c0819092637e0d83ce8ac0 completed May 10, 2026, 12:10 p.m.
NEDg Description generation batch_6a00783fcde08190963ce80fcf4aac90 completed May 10, 2026, 12:21 p.m.
NED2 Entity disambiguation (via description) batch_6a0078a78ee08190887e93c08edbaead completed May 10, 2026, 12:23 p.m.
Created at: April 10, 2026, 5:17 a.m.