Triple

T14917753
Position Surface form Disambiguated ID Type / Status
Subject Swiss nobility E371424 entity
Predicate includesTitle P3254 FINISHED
Object Junker
Junker is a historical noble title, particularly associated with the lower-ranking landed aristocracy in German-speaking regions, including parts of Switzerland.
E1126801 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: Junker | Statement: [Swiss nobility, includesTitle, Junker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Junker
Context triple: [Swiss nobility, includesTitle, Junker]
  • A. Junker Jörg
    Junker Jörg was the alias used by Martin Luther while he lived in hiding at Wartburg Castle, during which he translated the New Testament into German.
  • B. Heinrici
    Heinrici is a German surname most notably associated with Gotthard Heinrici, a senior Wehrmacht general during World War II.
  • C. Günther
    Günther is the zoologist who first formally described the impressed tortoise species Manouria impressa.
  • D. Günther
    Günther is a German masculine given name traditionally associated with figures of Germanic origin and culture.
  • E. Leiningen
    Leiningen is a popular build automation and project management tool for the Clojure programming language, used to manage dependencies, run tasks, and streamline development workflows.
  • 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: Junker
Triple: [Swiss nobility, includesTitle, Junker]
Generated description
Junker is a historical noble title, particularly associated with the lower-ranking landed aristocracy in German-speaking regions, including parts of Switzerland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Junker
Target entity description: Junker is a historical noble title, particularly associated with the lower-ranking landed aristocracy in German-speaking regions, including parts of Switzerland.
  • A. Junker Jörg
    Junker Jörg was the alias used by Martin Luther while he lived in hiding at Wartburg Castle, during which he translated the New Testament into German.
  • B. Heinrici
    Heinrici is a German surname most notably associated with Gotthard Heinrici, a senior Wehrmacht general during World War II.
  • C. Günther
    Günther is a German masculine given name traditionally associated with figures of Germanic origin and culture.
  • D. Günther
    Günther is the zoologist who first formally described the impressed tortoise species Manouria impressa.
  • E. Leiningen
    Leiningen is a popular build automation and project management tool for the Clojure programming language, used to manage dependencies, run tasks, and streamline development workflows.
  • 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_69d85cc7ea3481908228b5acb7d06f12 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded62038508190946499cd3552990e completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe72bf2120819099df39bdc1da691b completed May 8, 2026, 11:33 p.m.
NEDg Description generation batch_69fe7360c11481908e2e5127b466e31b completed May 8, 2026, 11:36 p.m.
NED2 Entity disambiguation (via description) batch_69fe743c37308190a045ef5f0ade8508 completed May 8, 2026, 11:39 p.m.
Created at: April 10, 2026, 2:32 a.m.