Triple

T14920982
Position Surface form Disambiguated ID Type / Status
Subject A5 E371506 entity
Predicate connectsToCountryViaTunnel P99274 FINISHED
Object France E861 NE FINISHED

How this triple was built (3 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: France | Statement: [A5, connectsToCountryViaTunnel, France]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: France
Context triple: [A5, connectsToCountryViaTunnel, France]
  • A. France chosen
    France is a major Western European nation known for its influential history, culture, and economy, and as a founding member of the European Union and the United Nations.
  • B. Francia
    Francia is the surname of American rower and two-time Olympic gold medalist Susan Francia.
  • C. Pays Royannais
    Pays Royannais is a coastal area in southwestern France centered around the town of Royan, known for its seaside resorts and Atlantic beaches.
  • D. de France
    "de France" is a dynastic surname historically used by members of the French royal family, particularly the legitimate children of reigning kings of France.
  • E. Francie
    Francie is a diminutive given name, typically used as a nickname for Francis or Frances.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: connectsToCountryViaTunnel
Context triple: [A5, connectsToCountryViaTunnel, France]
  • A. usesTunnel
    Indicates that one entity makes use of a tunnel as a passage or route to reach or connect to another entity.
  • B. connectsCountryOrRegion chosen
    Indicates that one entity establishes a connection, link, or association to a specific country or region.
  • C. usesTunnelOrBridge
    Indicates that one entity travels or passes between locations by means of a tunnel or a bridge.
  • D. connectsCountryDirection
    Indicates that one country is geographically connected to another in a specified cardinal or relative direction (e.g., north, south, east, west).
  • E. tunnelType
    Indicates the specific kind or classification of a tunnel associated with an entity.
  • F. None of above.

Provenance (4 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_69d85cc7ea3481908228b5acb7d06f12 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded63121e48190b54eb2546acc3c93 completed April 15, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe72b11584819084f32516cb0023a1 completed May 8, 2026, 11:33 p.m.
PD Predicate disambiguation batch_69de9a52ba988190a26e268b4ea083ea completed April 14, 2026, 7:49 p.m.
Created at: April 10, 2026, 2:33 a.m.