Triple

T17508552
Position Surface form Disambiguated ID Type / Status
Subject Battenberg family E426389 entity
Predicate namedAfter P63 FINISHED
Object Battenberg, Hesse
Battenberg, Hesse is a small town in central Germany best known as the ancestral seat of the Battenberg (later Mountbatten) noble family.
E1272698 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: Battenberg, Hesse | Statement: [Battenberg family, namedAfter, Battenberg, Hesse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Battenberg, Hesse
Context triple: [Battenberg family, namedAfter, Battenberg, Hesse]
  • A. Abensberg
    Abensberg is a historic town in Bavaria, Germany, known for its medieval architecture and its role as a Napoleonic-era battlefield.
  • B. Hesse-Rotenburg
    Hesse-Rotenburg was a small German landgraviate and cadet branch territory of the House of Hesse within the Holy Roman Empire.
  • C. Hesse-Bessungen
    Hesse-Bessungen was a cadet branch of the German princely House of Hesse-Darmstadt, associated with the Bessungen area near Darmstadt.
  • D. Hesse-Braubach
    Hesse-Braubach was a minor cadet line of the German princely House of Hesse-Darmstadt, centered around the town of Braubach.
  • E. Friedberg, Hesse
    Friedberg, Hesse is a historic town in central Germany’s state of Hesse, known for its medieval architecture and prominent hilltop fortress.
  • 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: Battenberg, Hesse
Triple: [Battenberg family, namedAfter, Battenberg, Hesse]
Generated description
Battenberg, Hesse is a small town in central Germany best known as the ancestral seat of the Battenberg (later Mountbatten) noble family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Battenberg, Hesse
Target entity description: Battenberg, Hesse is a small town in central Germany best known as the ancestral seat of the Battenberg (later Mountbatten) noble family.
  • A. Abensberg
    Abensberg is a historic town in Bavaria, Germany, known for its medieval architecture and its role as a Napoleonic-era battlefield.
  • B. Hesse-Rotenburg
    Hesse-Rotenburg was a small German landgraviate and cadet branch territory of the House of Hesse within the Holy Roman Empire.
  • C. Hesse-Bessungen
    Hesse-Bessungen was a cadet branch of the German princely House of Hesse-Darmstadt, associated with the Bessungen area near Darmstadt.
  • D. Hesse-Braubach
    Hesse-Braubach was a minor cadet line of the German princely House of Hesse-Darmstadt, centered around the town of Braubach.
  • E. Friedberg, Hesse
    Friedberg, Hesse is a historic town in central Germany’s state of Hesse, known for its medieval architecture and prominent hilltop fortress.
  • 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_69d889dd9164819087b1dc3c9240c870 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4525985f881909a5ad28b30762680 completed April 19, 2026, 3:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01c20cbf8081909227938b324e45fe completed May 11, 2026, 11:48 a.m.
NEDg Description generation batch_6a01c388d87c8190ad015b2b63bef528 completed May 11, 2026, 11:54 a.m.
NED2 Entity disambiguation (via description) batch_6a01c431b4608190b5636a232ff46733 completed May 11, 2026, 11:57 a.m.
Created at: April 10, 2026, 5:48 a.m.