Triple

T35289727
Position Surface form Disambiguated ID Type / Status
Subject Steven Stayner E1019187 entity
Predicate kidnapper P182692 FINISHED
Object Kenneth Parnell
Kenneth Parnell was an American child molester and kidnapper best known for abducting Steven Stayner in 1972 and holding him captive for seven years.
E2135351 NE FINISHED

How this triple was built (3 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: Kenneth Parnell | Statement: [Steven Stayner, kidnapper, Kenneth Parnell]
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: Kenneth Parnell
Triple: [Steven Stayner, kidnapper, Kenneth Parnell]
Generated description
Kenneth Parnell was an American child molester and kidnapper best known for abducting Steven Stayner in 1972 and holding him captive for seven years.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: kidnapper
Context triple: [Steven Stayner, kidnapper, Kenneth Parnell]
  • A. wasKidnapped
    Indicates that an entity was forcibly taken and held against their will by another entity.
  • B. kidnappedIn
    Indicates that an entity was forcibly taken or abducted within, or as part of an event occurring in, a specified location or context.
  • C. ageAtKidnapping
    Indicates the age a person was at the time they were kidnapped.
  • D. oftenKidnaps
    Indicates that one entity frequently or habitually kidnaps another entity.
  • E. abductedBy
    Indicates that an entity has been forcibly taken or carried away by another entity against their will.
  • F. None of above. chosen

Provenance (7 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_69f76de6d39c8190bb11342e4b91ff2b completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69f7904a770481908ef3f788e51e8dba completed May 3, 2026, 6:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3819df117481908ccbd686ca6f243e completed June 21, 2026, 5:05 p.m.
NEDg Description generation batch_6a381ad38af88190a5a799b1651b8840 completed June 21, 2026, 5:09 p.m.
NED2 Entity disambiguation (via description) batch_6a381b78cc2c8190adcfc95407d338e8 completed June 21, 2026, 5:12 p.m.
PD Predicate disambiguation batch_69f78e2f52e08190a77661223a96c601 completed May 3, 2026, 6:04 p.m.
PDg Predicate description generation batch_69f78f629d508190b755848162c4e101 completed May 3, 2026, 6:09 p.m.
Created at: May 3, 2026, 4:03 p.m.