Triple

T6435337
Position Surface form Disambiguated ID Type / Status
Subject SAP Concur E129879 entity
Predicate owner P347 FINISHED
Object SAP SE E35622 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: SAP SE | Statement: [SAP Concur, owner, SAP SE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SAP SE
Context triple: [SAP Concur, owner, SAP SE]
  • A. SAP
    SAP is the station code for Lisbon Santa Apolónia, one of the main railway terminals in Lisbon, Portugal.
  • B. SAP
    SAP is Sweden’s major center-left political party, historically associated with social democracy, the welfare state, and long periods of governing the country.
  • C. SAP
    SAP was the former official currency of South Africa, used before the adoption of the South African rand.
  • D. SAP chosen
    SAP is a leading global enterprise software company best known for its ERP solutions that help organizations manage business operations and customer relations.
  • E. SAP
    SAP is the commonly used abbreviation for the Société d’Anthropologie de Paris, a French learned society dedicated to the study of anthropology.
  • 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_69c0084caac48190a7bc2ad8ba44536f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c069415c3c8190b91bd12ae79edd26 completed March 22, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6538ca31c8190b4a24662c4eeffe9 completed March 27, 2026, 9:53 a.m.
Created at: March 22, 2026, 4:45 p.m.