Triple

T24453965
Position Surface form Disambiguated ID Type / Status
Subject John IV of Armagnac E616625 entity
Predicate mother P120 FINISHED
Object Margaret of Comminges
Margaret of Comminges was a medieval French noblewoman from the House of Comminges who became Countess of Armagnac and the mother of John IV of Armagnac.
 E1929888 NE FINISHED

How this triple was built (2 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 of Comminges | Statement: [John IV of Armagnac, mother, Margaret of Comminges]
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 of Comminges
Triple: [John IV of Armagnac, mother, Margaret of Comminges]
Generated description
Margaret of Comminges was a medieval French noblewoman from the House of Comminges who became Countess of Armagnac and the mother of John IV of Armagnac.

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_69e2d7ef9fe08190a0613908758b4e86 completed April 18, 2026, 1:01 a.m.
NER Named-entity recognition batch_69f298c4f1d881909d9119fec74afe53 completed April 29, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2898afbcac819090a462e0ddb1dc56 completed June 9, 2026, 10:50 p.m.
NEDg Description generation batch_6a289987c9988190a355050ae3113a08 completed June 9, 2026, 10:53 p.m.
NED2 Entity disambiguation (via description) batch_6a289d68dafc8190a4624b6bc4f54b9c completed June 9, 2026, 11:10 p.m.
Created at: April 18, 2026, 2:18 a.m.