Triple

T3565522
Position Surface form Disambiguated ID Type / Status
Subject Maria Pia Bridge E75438 entity
Predicate engineer P184 FINISHED
Object Théophile Seyrig E491833 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: Théophile Seyrig | Statement: [Maria Pia Bridge, engineer, Théophile Seyrig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Théophile Seyrig
Context triple: [Maria Pia Bridge, engineer, Théophile Seyrig]
  • A. Théophile Seyrig chosen
    Théophile Seyrig was a 19th-century German engineer best known for his work with Gustave Eiffel and for designing notable iron bridges in Portugal.
  • B. Pierre Montet
    Pierre Montet was a French Egyptologist renowned for his excavations and discoveries in ancient Egyptian sites, particularly royal tombs.
  • C. Jean-Louis Blondeau
    Jean-Louis Blondeau is a French photographer and filmmaker best known for documenting Philippe Petit’s 1974 high-wire walk between the Twin Towers, featured in the documentary "Man on Wire."
  • D. André Massoulle
    André Massoulle was a French sculptor known for contributing decorative statuary to major Parisian monuments in the late 19th and early 20th centuries.
  • E. Pierre Lacotte
    Pierre Lacotte was a renowned French choreographer and ballet master celebrated for reviving and reconstructing 19th-century Romantic ballets.
  • 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_69ad85d512708190829c8b2d3a2ccfb8 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0a8f6288190928479f5bea32245 completed March 8, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69beba392ad08190a66ccf58edecb722 completed March 21, 2026, 3:33 p.m.
Created at: March 8, 2026, 3:21 p.m.