Triple

T19468813
Position Surface form Disambiguated ID Type / Status
Subject Manfred Korfmann E487067 entity
Predicate familyName P18 FINISHED
Object Korfmann
Korfmann is a German surname most notably associated with archaeologist Manfred Korfmann, known for his excavations at the ancient site of Troy.
E1377492 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: Korfmann | Statement: [Manfred Korfmann, familyName, Korfmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Korfmann
Context triple: [Manfred Korfmann, familyName, Korfmann]
  • A. Jungmann
    Jungmann is the nickname of the Bücker Bü 131, a German 1930s biplane widely used as a primary trainer aircraft before and during World War II.
  • B. Klostermann
    Klostermann is a German academic publishing house known for its influential works in philosophy and the humanities.
  • C. Marloffstein
    Marloffstein is a small municipality in the Erlangen-Höchstadt district of Bavaria, Germany, known for its rural character and proximity to the city of Erlangen.
  • D. Bischoffen
    Bischoffen is a small municipality in the central German state of Hesse, situated in a rural area characterized by forests, hills, and nearby reservoirs.
  • E. Bonnke
    Bonnke is a German surname most prominently associated with Reinhard Bonnke, a well-known Christian evangelist.
  • 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: Korfmann
Triple: [Manfred Korfmann, familyName, Korfmann]
Generated description
Korfmann is a German surname most notably associated with archaeologist Manfred Korfmann, known for his excavations at the ancient site of Troy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Korfmann
Target entity description: Korfmann is a German surname most notably associated with archaeologist Manfred Korfmann, known for his excavations at the ancient site of Troy.
  • A. Jungmann
    Jungmann is the nickname of the Bücker Bü 131, a German 1930s biplane widely used as a primary trainer aircraft before and during World War II.
  • B. Klostermann
    Klostermann is a German academic publishing house known for its influential works in philosophy and the humanities.
  • C. Marloffstein
    Marloffstein is a small municipality in the Erlangen-Höchstadt district of Bavaria, Germany, known for its rural character and proximity to the city of Erlangen.
  • D. Bischoffen
    Bischoffen is a small municipality in the central German state of Hesse, situated in a rural area characterized by forests, hills, and nearby reservoirs.
  • E. Bonnke
    Bonnke is a German surname most prominently associated with Reinhard Bonnke, a well-known Christian evangelist.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633e4b230819097c8804ee91988ea completed April 20, 2026, 2:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a073b41f34c8190abc737a01bc09973 completed May 15, 2026, 3:26 p.m.
NEDg Description generation batch_6a073bd8fd108190b4aa79dcdf3c2758 completed May 15, 2026, 3:29 p.m.
NED2 Entity disambiguation (via description) batch_6a073c574c808190b2ae6df5477c27bb completed May 15, 2026, 3:31 p.m.
Created at: April 10, 2026, 1:39 p.m.