Triple

T13841970
Position Surface form Disambiguated ID Type / Status
Subject Compans E332678 entity
Predicate locatedInBasin P18951 FINISHED
Object Paris Basin E55844 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: Paris Basin | Statement: [Compans, locatedInBasin, Paris Basin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paris Basin
Context triple: [Compans, locatedInBasin, Paris Basin]
  • A. Paris Basin chosen
    The Paris Basin is a large sedimentary basin in northern France known for its gently rolling plains, fertile agricultural land, and significant geological and paleontological formations.
  • B. Aquitaine Basin
    The Aquitaine Basin is a large sedimentary basin in southwestern France known for its petroleum resources and varied geological formations.
  • C. Rhône plain
    The Rhône plain is a broad, fertile lowland region in southeastern France shaped by the Rhône River, known for its agriculture, vineyards, and historic settlements.
  • D. Allier basin
    The Allier basin is the drainage area of the Allier River in central France, encompassing its tributaries and surrounding watershed.
  • E. Marne River basin
    The Marne River basin is a major drainage area in northeastern France that collects the waters of the Marne River and its tributaries before they flow into the Seine.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02afce788190a74dce4e6a3569fa completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8f630d081909439e1cdc5d60430 completed May 3, 2026, 9:07 p.m.
Created at: April 9, 2026, 10:13 p.m.