Triple

T26567305
Position Surface form Disambiguated ID Type / Status
Subject Baron Botreaux E666721 entity
Predicate heldByMarriage P161581 FINISHED
Object Margaret Botreaux
Margaret Botreaux was an English noblewoman of the medieval period who became associated with the Barony of Botreaux through her marriage.
 E1732674 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: Margaret Botreaux | Statement: [Baron Botreaux, heldByMarriage, Margaret Botreaux]
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: Margaret Botreaux
Triple: [Baron Botreaux, heldByMarriage, Margaret Botreaux]
Generated description
Margaret Botreaux was an English noblewoman of the medieval period who became associated with the Barony of Botreaux through her marriage.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: heldByMarriage
Context triple: [Baron Botreaux, heldByMarriage, Margaret Botreaux]
  • A. hasMarriage
    Indicates a marital relationship exists between the two entities, specifying that they are or were legally married to each other.
  • B. involvesMarriage
    Indicates that the relationship or action includes or is characterized by a marriage between the involved entities.
  • C. marriageResolvedBy
    Indicates that a marital relationship between two parties has been formally concluded or dissolved through a specific resolving action or process (e.g., divorce, annulment).
  • D. marriageProvision
    Indicates that one party provides for, supports, or makes arrangements related to another party’s marriage (such as financial, legal, or material provisions).
  • E. marriageContext
    Indicates the situational or cultural circumstances under which a marriage occurs or exists, such as legal, social, or religious conditions surrounding the marital relationship.
  • 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_69ee9cfa21c081909e4e36e087debfc6 completed April 26, 2026, 11:17 p.m.
NER Named-entity recognition batch_69f61ad613608190855de13501a86007 completed May 2, 2026, 3:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a11c82a35ec8190bceda81f5c8b53a6 completed May 23, 2026, 3:30 p.m.
NEDg Description generation batch_6a11c919c3d08190ae5cc3a21f5257be completed May 23, 2026, 3:34 p.m.
NED2 Entity disambiguation (via description) batch_6a11ca2243988190a158631f4b94e205 completed May 23, 2026, 3:39 p.m.
PD Predicate disambiguation batch_69f611ab768c8190b1849c15a3e59dda completed May 2, 2026, 3 p.m.
PDg Predicate description generation batch_69f61a16b7848190bf20d2be7e5a16c1 completed May 2, 2026, 3:36 p.m.
Created at: April 27, 2026, 1:55 a.m.