Triple

T30855097
Position Surface form Disambiguated ID Type / Status
Subject Havelberg Cathedral E785897 entity
Predicate formerBishopSeatOf P198851 FINISHED
Object Bishop of Havelberg
The Bishop of Havelberg was a medieval ecclesiastical office overseeing a Catholic diocese in the town of Havelberg in present-day Germany.
 E1934711 NE FINISHED

How this triple was built (3 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: Bishop of Havelberg | Statement: [Havelberg Cathedral, formerBishopSeatOf, Bishop of Havelberg]
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: Bishop of Havelberg
Triple: [Havelberg Cathedral, formerBishopSeatOf, Bishop of Havelberg]
Generated description
The Bishop of Havelberg was a medieval ecclesiastical office overseeing a Catholic diocese in the town of Havelberg in present-day Germany.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: formerBishopSeatOf
Context triple: [Havelberg Cathedral, formerBishopSeatOf, Bishop of Havelberg]
  • A. formerBishop
    Indicates that a person once held the position of bishop but no longer occupies that office.
  • B. formerDiocese
    Indicates that an entity was once a diocese but no longer holds that diocesan status.
  • C. formerCathedralCity
    Indicates that a place was once recognized as a cathedral city but no longer holds that cathedral-city status.
  • D. wasEcclesiasticalPredecessor
    Indicates that one ecclesiastical officeholder held a given religious position before another, in a direct line of succession.
  • E. archbishopricPredecessor
    Indicates that one entity previously held the position of archbishop immediately before another entity in the same archbishopric office.
  • F. None of above. chosen

Provenance (7 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_69f224b91c14819084e764832fe67a57 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69ff0e9c75208190a4423261f00b79b3 completed May 9, 2026, 10:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a28bbfc88148190a2113f655d70145c completed June 10, 2026, 1:21 a.m.
NEDg Description generation batch_6a28bfe8b0708190a67937771c70fd8e completed June 10, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_6a28c05f27288190ad1e9108f289cfac completed June 10, 2026, 1:39 a.m.
PD Predicate disambiguation batch_69ff0e07f08481909c4ae322632a6bf0 completed May 9, 2026, 10:35 a.m.
PDg Predicate description generation batch_69ff0e9b7acc81909a0ee66201a06877 completed May 9, 2026, 10:38 a.m.
Created at: April 29, 2026, 8:46 p.m.