Triple

T4190663
Position Surface form Disambiguated ID Type / Status
Subject Count (continental Europe) E89025 entity
Predicate correspondsToTitle P10405 FINISHED
Object Graf (German) E151142 NE FINISHED

How this triple was built (2 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: Graf (German) | Statement: [Count (continental Europe), correspondsToTitle, Graf (German)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graf (German)
Context triple: [Count (continental Europe), correspondsToTitle, Graf (German)]
  • A. Graf (German-speaking countries)
    Graf is a historical noble title used in German-speaking countries, roughly equivalent in rank to an earl or count.
  • B. Graf chosen
    Graf is a historical German noble title roughly equivalent to a count in other European aristocratic systems.
  • C. Graf zu Waldeck
    Graf zu Waldeck is a noble title historically borne by members of the German princely House of Waldeck.
  • D. Roth (German)
    Roth (German) is a German-language surname and place name that commonly refers to various towns in Germany and to people of German origin bearing the name Roth.
  • E. Bramsche
    Bramsche is a town in Lower Saxony, Germany, known for its location near Osnabrück and its historical textile industry.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed9569a4481908b6c1fcec2a11e21 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af034019848190bd5486521c375325 completed March 9, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69b58a05e634819094bbe145f86d8786 completed March 14, 2026, 4:17 p.m.
Created at: March 9, 2026, 3:46 p.m.