Triple

T13100422
Position Surface form Disambiguated ID Type / Status
Subject 2nd Foreign Infantry Regiment E310702 entity
Predicate nickname P55 FINISHED
Object 2e REI E1020278 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: 2e REI | Statement: [2nd Foreign Infantry Regiment, nickname, 2e REI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 2e REI
Context triple: [2nd Foreign Infantry Regiment, nickname, 2e REI]
  • A. 2e REI chosen
    2e REI is a regiment of the French Foreign Legion renowned for its infantry combat role and deployments in overseas operations.
  • B. 2REI
    2REI is a regiment of the French Foreign Legion specializing in infantry operations, known for its rigorous training and deployments in overseas missions.
  • C. E-2A
    E-2A was the Soviet spacecraft bus platform used for early Luna missions such as Luna 3, which photographed the Moon’s far side.
  • D. Reen
    Reen is a shortened or familiar form of the given name Maureen.
  • E. E22
    E22 is a major European route that forms part of the international E-road network, linking multiple countries across Europe.
  • 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_69d806a872d08190a329806f8ff30df4 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d981515d488190908d3cca1b84a42d completed April 10, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e275df6c819096bb59e64df35216 completed May 3, 2026, 5:51 a.m.
Created at: April 9, 2026, 9:04 p.m.