Triple

T819034
Position Surface form Disambiguated ID Type / Status
Subject Erhard Milch E17711 entity
Predicate familyName P18 FINISHED
Object Milch
Milch is a German surname most notably borne by Erhard Milch, a high-ranking Luftwaffe officer during World War II.
 E98308 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: Milch | Statement: [Erhard Milch, familyName, Milch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Milch
Context triple: [Erhard Milch, familyName, Milch]
  • A. Milchbuck
    Milchbuck is a public transportation stop in Zurich, Switzerland, serving as a key access point to the nearby Irchel university campus and surrounding urban areas.
  • B. Malvids
    Malvids are a major clade of flowering plants within the rosids that includes economically important families such as Brassicaceae (mustards) and Malvaceae (mallows).
  • C. Het melkmeisje
    Het melkmeisje is a famous 17th-century painting by Dutch artist Johannes Vermeer depicting a kitchen maid pouring milk in a quiet domestic interior.
  • D. Bega
    Bega is a rural town in New South Wales, Australia, best known as a major dairy and cheese-producing centre.
  • E. Lick
    Lick is the nickname of Joseph Carl Robnett Licklider, a pioneering American computer scientist whose ideas helped lay the foundations for interactive computing and the internet.
  • 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: Milch
Triple: [Erhard Milch, familyName, Milch]
Generated description
Milch is a German surname most notably borne by Erhard Milch, a high-ranking Luftwaffe officer during World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Milch
Target entity description: Milch is a German surname most notably borne by Erhard Milch, a high-ranking Luftwaffe officer during World War II.
  • A. Milchbuck
    Milchbuck is a public transportation stop in Zurich, Switzerland, serving as a key access point to the nearby Irchel university campus and surrounding urban areas.
  • B. Malvids
    Malvids are a major clade of flowering plants within the rosids that includes economically important families such as Brassicaceae (mustards) and Malvaceae (mallows).
  • C. Het melkmeisje
    Het melkmeisje is a famous 17th-century painting by Dutch artist Johannes Vermeer depicting a kitchen maid pouring milk in a quiet domestic interior.
  • D. Bega
    Bega is a rural town in New South Wales, Australia, best known as a major dairy and cheese-producing centre.
  • E. Lick
    Lick is the nickname of Joseph Carl Robnett Licklider, a pioneering American computer scientist whose ideas helped lay the foundations for interactive computing and the internet.
  • 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_69a4937bcaac8190a322524ac6f45a5a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4ab656418819091ecb09e7ede2825 completed March 1, 2026, 9:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a76d8f639081909690d1ef4c98680e completed March 3, 2026, 11:23 p.m.
NEDg Description generation batch_69a781f5536c81908175d58b6b75adba completed March 4, 2026, 12:51 a.m.
NED2 Entity disambiguation (via description) batch_69a7860e656c8190a08a9999662ba1f1 completed March 4, 2026, 1:08 a.m.
Created at: March 1, 2026, 7:38 p.m.