Triple

T4653968
Position Surface form Disambiguated ID Type / Status
Subject Erik Carlsson E102362 entity
Predicate team P3756 FINISHED
Object Saab works team E2751 NE FINISHED

How this triple was built (2 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: Saab works team | Statement: [Erik Carlsson, team, Saab works team]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saab works team
Context triple: [Erik Carlsson, team, Saab works team]
  • A. Saab AB
    Saab AB is a Swedish aerospace and defense company known for developing military aircraft, advanced defense systems, and security solutions.
  • B. Saab Kockums
    Saab Kockums is a Swedish shipyard and defense company best known for designing and building advanced submarines and naval vessels.
  • C. SAAB B
    SAAB B is a class of publicly traded shares representing ownership in the Swedish aerospace and defense company Saab AB.
  • D. Saab Surveillance
    Saab Surveillance is a business unit of the Swedish defense and security company Saab AB that specializes in advanced radar, sensor, and command-and-control systems for military and civil applications.
  • E. Saab Automobile chosen
    Saab Automobile was a Swedish car manufacturer known for its innovative engineering, turbocharged engines, and distinctive, safety-focused designs.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd43d71a308190afea7280841b0de8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd631623d881908a59dafa7702af54 completed March 20, 2026, 3:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfaef125c819097d79f25608302dc completed March 21, 2026, 1:57 a.m.
Created at: March 20, 2026, 1:14 p.m.