Triple

T6485316
Position Surface form Disambiguated ID Type / Status
Subject Henri Rousseau E146493 entity
Predicate employer P7 FINISHED
Object Paris customs office E60480 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 customs office | Statement: [Henri Rousseau, employer, Paris customs office]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paris customs office
Context triple: [Henri Rousseau, employer, Paris customs office]
  • A. French customs authorities chosen
    French customs authorities were the state officials responsible for regulating and policing France’s borders and trade, particularly during the Napoleonic era.
  • B. Port of Paris
    The Port of Paris is a major inland port complex in the Île-de-France region that handles river traffic, logistics, and tourism along the Seine and its connected waterways.
  • C. Porte de Paris
    Porte de Paris is a historic city gate in Cambrai, France, notable for its monumental architecture and role as a former entrance to the fortified town.
  • D. Fontainebleau, France
    Fontainebleau, France is a historic town southeast of Paris best known for its vast forest and royal château, long associated with French monarchs and outdoor recreation.
  • E. Paris Qualles
    Paris Qualles is an American television and film screenwriter and producer known for his work on socially conscious dramas and biographical projects.
  • 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_69c0090158c08190af0df9a2348d2d52 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c06a6efe1881909a044b1cdaa511af completed March 22, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c653b24670819088fa8e0d7eb6f73b completed March 27, 2026, 9:53 a.m.
Created at: March 22, 2026, 4:52 p.m.