Triple

T33976078
Position Surface form Disambiguated ID Type / Status
Subject Rose McIver E871142 entity
Predicate spouse P13 FINISHED
Object Benjamin Hoeksema (former partner)
Benjamin Hoeksema is a New Zealand architect best known for his long-term former relationship with actress Rose McIver.
E2075392 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: Benjamin Hoeksema (former partner) | Statement: [Rose McIver, spouse, Benjamin Hoeksema (former partner)]
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: Benjamin Hoeksema (former partner)
Triple: [Rose McIver, spouse, Benjamin Hoeksema (former partner)]
Generated description
Benjamin Hoeksema is a New Zealand architect best known for his long-term former relationship with actress Rose McIver.

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_69f3499da0188190ab1a4ff06fb06a2a completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f7032a8e188190b889dc95dee59b65 completed May 3, 2026, 8:11 a.m.
NED1 Entity disambiguation (via context triple) batch_6a3689f292bc8190ae5e87d502a1d8ce completed June 20, 2026, 12:39 p.m.
NEDg Description generation batch_6a368a76844c8190a7b85efae4d34fd5 completed June 20, 2026, 12:41 p.m.
NED2 Entity disambiguation (via description) batch_6a368b58c7848190b708ded1bbc44b60 completed June 20, 2026, 12:45 p.m.
Created at: May 1, 2026, 1:50 a.m.