Triple

T9971996
Position Surface form Disambiguated ID Type / Status
Subject Bernhard Heisig E196229 entity
Predicate familyName P18 FINISHED
Object Heisig
Heisig is a German surname most notably associated with Bernhard Heisig, a prominent painter linked to the Leipzig School and postwar East German art.
 E832258 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: Heisig | Statement: [Bernhard Heisig, familyName, Heisig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heisig
Context triple: [Bernhard Heisig, familyName, Heisig]
  • A. Wheelock
    Wheelock is a surname most notably associated with Eleazar Wheelock, the 18th-century American Congregational minister and founder of Dartmouth College.
  • B. Kana
    Kana is the Japanese syllabic writing system comprising hiragana and katakana, used to represent native words, grammatical elements, and foreign terms.
  • C. Kana
    Kana is a settlement located within Pakistan’s Shangla District in the Khyber Pakhtunkhwa province.
  • D. Pe̍h-ōe-jī
    Pe̍h-ōe-jī is a Latin-based orthography developed by Western missionaries for writing Southern Min (Hokkien) and related Chinese dialects.
  • E. Kanji
    Kanji are logographic characters of Chinese origin used in the Japanese writing system alongside hiragana and katakana.
  • 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: Heisig
Triple: [Bernhard Heisig, familyName, Heisig]
Generated description
Heisig is a German surname most notably associated with Bernhard Heisig, a prominent painter linked to the Leipzig School and postwar East German art.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Heisig
Target entity description: Heisig is a German surname most notably associated with Bernhard Heisig, a prominent painter linked to the Leipzig School and postwar East German art.
  • A. Wheelock
    Wheelock is a surname most notably associated with Eleazar Wheelock, the 18th-century American Congregational minister and founder of Dartmouth College.
  • B. Kana
    Kana is the Japanese syllabic writing system comprising hiragana and katakana, used to represent native words, grammatical elements, and foreign terms.
  • C. Kana
    Kana is a settlement located within Pakistan’s Shangla District in the Khyber Pakhtunkhwa province.
  • D. Pe̍h-ōe-jī
    Pe̍h-ōe-jī is a Latin-based orthography developed by Western missionaries for writing Southern Min (Hokkien) and related Chinese dialects.
  • E. Kanji
    Kanji are logographic characters of Chinese origin used in the Japanese writing system alongside hiragana and katakana.
  • 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_69ca82eea2b88190a0e511d21a31f386 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb7bb03688190a3f4fc1988b8fafa completed April 2, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23dd3e47c819095fef68b9939ec19 completed April 5, 2026, 10:47 a.m.
NEDg Description generation batch_69d23eb2971c8190bcdbc31b4ef19816 completed April 5, 2026, 10:51 a.m.
NED2 Entity disambiguation (via description) batch_69d240d7b7e881909183d7c33bd8cb5b completed April 5, 2026, 11 a.m.
Created at: March 30, 2026, 8:48 p.m.