Triple

T2737189
Position Surface form Disambiguated ID Type / Status
Subject Hans Luther E60657 entity
Predicate familyName P18 FINISHED
Object Luther
Luther is a common German surname most famously associated with the Protestant Reformer Martin Luther and his family.
E301959 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: Luther | Statement: [Hans Luther, familyName, Luther]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luther
Context triple: [Hans Luther, familyName, Luther]
  • A. Luther
    Luther is a masculine given name of Germanic origin, most famously borne by civil rights leader Martin Luther King Jr. and R&B singer Luther Vandross.
  • B. Luther
    Luther is a British psychological crime drama television series starring Idris Elba as a brilliant but troubled detective.
  • C. Martin Luther
    Martin Luther was a 16th-century German theologian and key figure of the Protestant Reformation whose teachings challenged Catholic doctrine and reshaped Western Christianity.
  • D. Martin Franz Luther
    Martin Franz Luther was a German Nazi diplomat and SS official who served in the Foreign Office and participated in the administration of the Holocaust.
  • E. Huldrych Zwingli
    Huldrych Zwingli was a leading Swiss Protestant Reformer whose theological ideas helped lay the groundwork for later Reformed traditions, including Calvinism.
  • 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: Luther
Triple: [Hans Luther, familyName, Luther]
Generated description
Luther is a common German surname most famously associated with the Protestant Reformer Martin Luther and his family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Luther
Target entity description: Luther is a common German surname most famously associated with the Protestant Reformer Martin Luther and his family.
  • A. Luther
    Luther is a British psychological crime drama television series starring Idris Elba as a brilliant but troubled detective.
  • B. Luther
    Luther is a masculine given name of Germanic origin, most famously borne by civil rights leader Martin Luther King Jr. and R&B singer Luther Vandross.
  • C. Martin Luther
    Martin Luther was a 16th-century German theologian and key figure of the Protestant Reformation whose teachings challenged Catholic doctrine and reshaped Western Christianity.
  • D. Martin Franz Luther
    Martin Franz Luther was a German Nazi diplomat and SS official who served in the Foreign Office and participated in the administration of the Holocaust.
  • E. Huldrych Zwingli
    Huldrych Zwingli was a leading Swiss Protestant Reformer whose theological ideas helped lay the groundwork for later Reformed traditions, including Calvinism.
  • 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_69ab4b77febc819095603eb012cd141b completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdb12e03c8190b270c814ce47b626 completed March 7, 2026, 8 a.m.
NED1 Entity disambiguation (via context triple) batch_69afce859ffc8190b88f82af50238215 completed March 10, 2026, 7:55 a.m.
NEDg Description generation batch_69afd0d11290819086331ed160799819 completed March 10, 2026, 8:05 a.m.
NED2 Entity disambiguation (via description) batch_69afd12d634c8190940d73465aa8158c completed March 10, 2026, 8:07 a.m.
Created at: March 6, 2026, 9:56 p.m.