Triple

T17364146
Position Surface form Disambiguated ID Type / Status
Subject Marechal (Portugal) E422143 entity
Predicate label P38 FINISHED
Object Marechal NE ONNED1

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: Marechal | Statement: [Marechal (Portugal), label, Marechal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marechal
Context triple: [Marechal (Portugal), label, Marechal]
  • A. Marechal chosen
    Marechal is the highest Portuguese Army rank, equivalent to a field marshal, typically reserved for wartime or exceptional command.
  • B. Mariscal
    Mariscal is a Spanish surname most notably associated with designer and illustrator Javier Mariscal, known for his influential work in graphic design and visual art.
  • C. Senapati
    Senapati was the commander-in-chief of the Maratha military forces, responsible for leading armies and overseeing warfare in the Maratha Empire.
  • D. Colonel General
    Colonel General is a high-ranking military officer rank, typically above major general and lieutenant general and just below the highest general ranks in several countries' armed forces.
  • E. Marchal
    Marchal is a fine-dining restaurant at Copenhagen’s historic Hôtel d’Angleterre, known for its elegant Nordic-French cuisine and refined atmosphere.
  • 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_69d889d6535c81908be333c01deaec4e completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a4f52988190847230e119a35b87 completed April 19, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01956294ec819083c1dde8fc2685e4 in_progress May 11, 2026, 8:37 a.m.
Created at: April 10, 2026, 5:44 a.m.