Triple

T16412915
Position Surface form Disambiguated ID Type / Status
Subject Sturmgewehr 57 E398608 entity
Predicate hasVariant P455 FINISHED
Object PE 57
PE 57 is a semi-automatic civilian rifle variant of the Swiss Sturmgewehr 57 battle rifle, designed primarily for sporting and target shooting use.
 E1211281 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: PE 57 | Statement: [Sturmgewehr 57, hasVariant, PE 57]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PE 57
Context triple: [Sturmgewehr 57, hasVariant, PE 57]
  • A. PE5
    PE5 is a postcode district in the PE (Peterborough) postcode area of eastern England, covering a small rural region near Peterborough.
  • B. P75
    P75 is an early 3rd-century Greek papyrus manuscript containing significant portions of the Gospels of Luke and John, valued for its importance in New Testament textual criticism.
  • C. PB-05
    PB-05 is the regional vehicle registration code assigned to the Ferozepur district in the Indian state of Punjab.
  • D. PEL
    PEL is the common abbreviation for the Lahti Pelicans, a professional ice hockey team based in Lahti, Finland.
  • E. PEEN
    PEEN is a continent-wide ecological network initiative aimed at connecting and conserving natural habitats and biodiversity across Europe.
  • 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: PE 57
Triple: [Sturmgewehr 57, hasVariant, PE 57]
Generated description
PE 57 is a semi-automatic civilian rifle variant of the Swiss Sturmgewehr 57 battle rifle, designed primarily for sporting and target shooting use.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PE 57
Target entity description: PE 57 is a semi-automatic civilian rifle variant of the Swiss Sturmgewehr 57 battle rifle, designed primarily for sporting and target shooting use.
  • A. PE5
    PE5 is a postcode district in the PE (Peterborough) postcode area of eastern England, covering a small rural region near Peterborough.
  • B. P75
    P75 is an early 3rd-century Greek papyrus manuscript containing significant portions of the Gospels of Luke and John, valued for its importance in New Testament textual criticism.
  • C. PB-05
    PB-05 is the regional vehicle registration code assigned to the Ferozepur district in the Indian state of Punjab.
  • D. PEL
    PEL is the common abbreviation for the Lahti Pelicans, a professional ice hockey team based in Lahti, Finland.
  • E. PEEN
    PEEN is a continent-wide ecological network initiative aimed at connecting and conserving natural habitats and biodiversity across Europe.
  • 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_69d87f2950248190bc8ad9b9bebdc8c8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32875bad08190bc3e2218df8c1b07 completed April 18, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003c68b7408190a9612a57f146dc30 completed May 10, 2026, 8:06 a.m.
NEDg Description generation batch_6a003db7b0308190bc4b8065cf2c01ec completed May 10, 2026, 8:11 a.m.
NED2 Entity disambiguation (via description) batch_6a003e86a9f48190ae39ec170c776604 completed May 10, 2026, 8:15 a.m.
Created at: April 10, 2026, 5:09 a.m.