Triple

T24671673
Position Surface form Disambiguated ID Type / Status
Subject Otto de la Roche E610852 entity
Predicate familyName P18 FINISHED
Object de la Roche
De la Roche is a French noble family name historically associated with medieval lords and crusader nobility, particularly in Greece.
 E1644727 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: de la Roche | Statement: [Otto de la Roche, familyName, de la Roche]
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: de la Roche
Triple: [Otto de la Roche, familyName, de la Roche]
Generated description
De la Roche is a French noble family name historically associated with medieval lords and crusader nobility, particularly in Greece.

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_69e2c4d505cc8190981881df06c0bf52 completed April 17, 2026, 11:40 p.m.
NER Named-entity recognition batch_69f40fab85488190987598a0ee23221d completed May 1, 2026, 2:27 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1004a788dc819097f8ed9e34547e52 completed May 22, 2026, 7:24 a.m.
NEDg Description generation batch_6a1006d3f07c819094102eafb5888ab0 completed May 22, 2026, 7:33 a.m.
NED2 Entity disambiguation (via description) batch_6a10074a63fc8190830385852e756e50 completed May 22, 2026, 7:35 a.m.
Created at: April 18, 2026, 2:43 a.m.