Triple

T23070519
Position Surface form Disambiguated ID Type / Status
Subject Gerrit Krol E575179 entity
Predicate employer P7 FINISHED
Object Royal Dutch Shell NE NERFINISHED

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: Royal Dutch Shell | Statement: [Gerrit Krol, employer, Royal Dutch Shell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Royal Dutch Shell
Context triple: [Gerrit Krol, employer, Royal Dutch Shell]
  • A. Royal Dutch Shell chosen
    Royal Dutch Shell is a major British-Dutch multinational oil and gas company and one of the largest energy corporations in the world.
  • B. British Petroleum
    British Petroleum is a major British multinational oil and gas company involved in exploration, production, refining, and energy trading worldwide.
  • C. Nederlandse Aardolie Maatschappij
    Nederlandse Aardolie Maatschappij is a Dutch petroleum company best known for its role in extracting natural gas from the Groningen field, which has been linked to induced earthquakes in the region.
  • D. Aker BP
    Aker BP is a Norwegian oil and gas exploration and production company and one of the largest independent operators on the Norwegian Continental Shelf.
  • E. Equinor
    Equinor is a Norwegian state-owned energy company and one of the world’s leading producers of oil, gas, and increasingly renewable energy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c5f17348190ab92cfdae9bcaeba completed April 29, 2026, 4:43 a.m.
Created at: April 17, 2026, 3:56 p.m.