Triple

T13000781
Position Surface form Disambiguated ID Type / Status
Subject Saab 18 E322162 entity
Predicate airForceDesignation P7137 FINISHED
Object S 18
S 18 is the Swedish Air Force designation for the Saab 18, a twin-engine bomber and reconnaissance aircraft used during and after World War II.
 E1015387 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: S 18 | Statement: [Saab 18, airForceDesignation, S 18]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: S 18
Context triple: [Saab 18, airForceDesignation, S 18]
  • A. S1
    S1 is a regional S-Bahn rail line within Germany’s Rhine-Ruhr metropolitan transit network, connecting key cities and suburbs in the area.
  • B. S1
    S1 is a key commuter rail line of the Berlin S-Bahn network, connecting central Berlin with its northern and southwestern suburbs.
  • C. S1
    S1 is a key commuter rail line of the Stuttgart S-Bahn network, connecting central Stuttgart with its surrounding suburbs and regional destinations.
  • D. S1
    S1 is a rapid transit line of the Hamburg S-Bahn network in Germany, connecting key suburbs with central Hamburg.
  • E. S1
    S1 is a commuter rail line within the Rhine-Main S-Bahn network serving the Frankfurt metropolitan region in Germany.
  • 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: S 18
Triple: [Saab 18, airForceDesignation, S 18]
Generated description
S 18 is the Swedish Air Force designation for the Saab 18, a twin-engine bomber and reconnaissance aircraft used during and after World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: S 18
Target entity description: S 18 is the Swedish Air Force designation for the Saab 18, a twin-engine bomber and reconnaissance aircraft used during and after World War II.
  • A. S1
    S1 is a regional S-Bahn rail line within Germany’s Rhine-Ruhr metropolitan transit network, connecting key cities and suburbs in the area.
  • B. S1
    S1 is a key commuter rail line of the Berlin S-Bahn network, connecting central Berlin with its northern and southwestern suburbs.
  • C. S1
    S1 is a key commuter rail line of the Stuttgart S-Bahn network, connecting central Stuttgart with its surrounding suburbs and regional destinations.
  • D. S1
    S1 is a rapid transit line of the Hamburg S-Bahn network in Germany, connecting key suburbs with central Hamburg.
  • E. S1
    S1 is a commuter rail line within the Rhine-Main S-Bahn network serving the Frankfurt metropolitan region in Germany.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e9828748190b2ad9ea29180b7d3 completed April 10, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c101ea60819098e4d5fb3a9e803a completed May 3, 2026, 3:29 a.m.
NEDg Description generation batch_69f6c277e6248190870b3bf9869716a7 completed May 3, 2026, 3:35 a.m.
NED2 Entity disambiguation (via description) batch_69f6c38bc0b08190b76cb0853d99ad82 completed May 3, 2026, 3:39 a.m.
Created at: April 9, 2026, 8:46 p.m.