Triple

T8058090
Position Surface form Disambiguated ID Type / Status
Subject Letter on Humanism E188048 entity
Predicate publisher P29 FINISHED
Object Klostermann
Klostermann is a German academic publishing house known for its influential works in philosophy and the humanities.
 E707150 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: Klostermann | Statement: [Letter on Humanism, publisher, Klostermann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Klostermann
Context triple: [Letter on Humanism, publisher, Klostermann]
  • A. Hartmann
    Hartmann is a German surname borne by numerous notable individuals across fields such as music, philosophy, and aviation.
  • B. Oberhauser
    Oberhauser is a German-language surname borne by various notable individuals across fields such as sports, the arts, and public life.
  • C. Sperrle
    Sperrle is a German surname most notably borne by Hugo Sperrle, a senior Luftwaffe field marshal during World War II.
  • D. Hammann
    Hammann is a German-origin surname borne by various notable individuals in fields such as aviation, music, and academia.
  • E. Morgenstern
    Morgenstern is a German surname borne by various notable figures in fields such as economics, literature, and the arts.
  • 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: Klostermann
Triple: [Letter on Humanism, publisher, Klostermann]
Generated description
Klostermann is a German academic publishing house known for its influential works in philosophy and the humanities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Klostermann
Target entity description: Klostermann is a German academic publishing house known for its influential works in philosophy and the humanities.
  • A. Hartmann
    Hartmann is a German surname borne by numerous notable individuals across fields such as music, philosophy, and aviation.
  • B. Oberhauser
    Oberhauser is a German-language surname borne by various notable individuals across fields such as sports, the arts, and public life.
  • C. Sperrle
    Sperrle is a German surname most notably borne by Hugo Sperrle, a senior Luftwaffe field marshal during World War II.
  • D. Hammann
    Hammann is a German-origin surname borne by various notable individuals in fields such as aviation, music, and academia.
  • E. Morgenstern
    Morgenstern is a German surname borne by various notable figures in fields such as economics, literature, and the arts.
  • 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_69ca82b2f68881908c50560697e210da completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3fa3dd2481909e925304fcea2111 completed March 31, 2026, 3:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc572a87788190a92f96f7b9c43f2a completed March 31, 2026, 11:22 p.m.
NEDg Description generation batch_69cc58ee56108190b93f0bf6bbb0321c completed March 31, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_69cc5cd22b188190b8a31e8e8ac8b98d completed March 31, 2026, 11:46 p.m.
Created at: March 30, 2026, 5:25 p.m.