Triple

T5178260
Position Surface form Disambiguated ID Type / Status
Subject Ehud E116853 entity
Predicate father P120 FINISHED
Object Gera
Gera is a biblical figure mentioned in the Hebrew Bible, known primarily as a Benjamite ancestor in the genealogy of the tribe of Benjamin.
 E501425 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: Gera | Statement: [Ehud, father, Gera]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gera
Context triple: [Ehud, father, Gera]
  • A. Gera
    Gera is a city in the German state of Thuringia, known for its industrial heritage and historic architecture along the White Elster river.
  • B. Eschwege
    Eschwege is a small historic town in the German state of Hesse, known for its medieval architecture and location near the Werra River.
  • C. Morava
    Morava is a Central European river that forms part of the border between Austria, the Czech Republic, and Slovakia before joining the Danube near Bratislava.
  • D. Lahn
    The Lahn is a river in western Germany that flows through the states of North Rhine-Westphalia, Hesse, and Rhineland-Palatinate before joining the Rhine.
  • E. Werre
    The Werre is a river in North Rhine-Westphalia, Germany, that flows through towns such as Detmold and Herford before joining the Weser.
  • 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: Gera
Triple: [Ehud, father, Gera]
Generated description
Gera is a biblical figure mentioned in the Hebrew Bible, known primarily as a Benjamite ancestor in the genealogy of the tribe of Benjamin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gera
Target entity description: Gera is a biblical figure mentioned in the Hebrew Bible, known primarily as a Benjamite ancestor in the genealogy of the tribe of Benjamin.
  • A. Gera
    Gera is a city in the German state of Thuringia, known for its industrial heritage and historic architecture along the White Elster river.
  • B. Eschwege
    Eschwege is a small historic town in the German state of Hesse, known for its medieval architecture and location near the Werra River.
  • C. Morava
    Morava is a Central European river that forms part of the border between Austria, the Czech Republic, and Slovakia before joining the Danube near Bratislava.
  • D. Lahn
    The Lahn is a river in western Germany that flows through the states of North Rhine-Westphalia, Hesse, and Rhineland-Palatinate before joining the Rhine.
  • E. Werre
    The Werre is a river in North Rhine-Westphalia, Germany, that flows through towns such as Detmold and Herford before joining the Weser.
  • 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_69bd446140f08190becb93c61158f27f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7976339481909ece900de22064f2 completed March 20, 2026, 4:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee07d20208190a423a9a395ac9d32 completed March 21, 2026, 6:16 p.m.
NEDg Description generation batch_69bee695358c8190801c63cff67efd1b completed March 21, 2026, 6:42 p.m.
NED2 Entity disambiguation (via description) batch_69bee6f91df48190adfcf47a63f4c8ef completed March 21, 2026, 6:44 p.m.
Created at: March 20, 2026, 1:45 p.m.