Triple

T9103667
Position Surface form Disambiguated ID Type / Status
Subject François Kellermann E218420 entity
Predicate familyName P18 FINISHED
Object Kellermann
Kellermann is a French surname most notably associated with François Christophe de Kellermann, a Marshal of France during the Napoleonic era.
E777107 NE FINISHED

How this triple was built (4 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: Kellermann | Statement: [François Kellermann, familyName, Kellermann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kellermann
Context triple: [François Kellermann, familyName, Kellermann]
  • A. Lützow
    Lützow was a German heavy cruiser (originally the pocket battleship Deutschland) that served in the Kriegsmarine during World War II.
  • B. Langsdorff
    Langsdorff is a German surname most notably associated with Hans Langsdorff, the captain of the World War II German pocket battleship Admiral Graf Spee.
  • C. Moltke
    Moltke is a small lunar impact crater located on the Moon’s near side near the Apollo 11 landing site in Mare Tranquillitatis.
  • D. Helmuth
    Helmuth is a masculine given name of German origin, historically borne by several notable military and political figures.
  • E. Oberroth
    Oberroth is a small municipality in the district of Neu-Ulm in the Bavarian region of Germany.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kellermann
Triple: [François Kellermann, familyName, Kellermann]
Generated description
Kellermann is a French surname most notably associated with François Christophe de Kellermann, a Marshal of France during the Napoleonic era.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kellermann
Target entity description: Kellermann is a French surname most notably associated with François Christophe de Kellermann, a Marshal of France during the Napoleonic era.
  • A. Lützow
    Lützow was a German heavy cruiser (originally the pocket battleship Deutschland) that served in the Kriegsmarine during World War II.
  • B. Langsdorff
    Langsdorff is a German surname most notably associated with Hans Langsdorff, the captain of the World War II German pocket battleship Admiral Graf Spee.
  • C. Moltke
    Moltke is a small lunar impact crater located on the Moon’s near side near the Apollo 11 landing site in Mare Tranquillitatis.
  • D. Helmuth
    Helmuth is a masculine given name of German origin, historically borne by several notable military and political figures.
  • E. Oberroth
    Oberroth is a small municipality in the district of Neu-Ulm in the Bavarian region of Germany.
  • F. None of above. chosen

Provenance (5 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_69ca83db7448819090d0a5de842ef2ac completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca56f1f10819091abadf7cd06c3a6 completed April 1, 2026, 4:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0183677cc8190b3140278f4c6de9c completed April 3, 2026, 7:42 p.m.
NEDg Description generation batch_69d0196766248190aebda80cbd7d1eef completed April 3, 2026, 7:47 p.m.
NED2 Entity disambiguation (via description) batch_69d019d76d2481909118b163ce5713f2 completed April 3, 2026, 7:49 p.m.
Created at: March 30, 2026, 7:15 p.m.