Triple

T23456291
Position Surface form Disambiguated ID Type / Status
Subject ProPublica E567930 entity
Predicate foundedBy P104 FINISHED
Object Herbert Sandler
Herbert Sandler was an American banker and philanthropist best known for co-founding the investigative journalism nonprofit ProPublica and previously leading Golden West Financial Corporation.
E1845285 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: Herbert Sandler | Statement: [ProPublica, foundedBy, Herbert Sandler]
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: Herbert Sandler
Triple: [ProPublica, foundedBy, Herbert Sandler]
Generated description
Herbert Sandler was an American banker and philanthropist best known for co-founding the investigative journalism nonprofit ProPublica and previously leading Golden West Financial Corporation.

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_69e2458b4c888190b1d7998f9862a558 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a6980d4481909fab47cb5bd28eab completed April 29, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a25057ab76881908f770a3f2f559b4e completed June 7, 2026, 5:45 a.m.
NEDg Description generation batch_6a2509a2a3b08190b3fde8083c80eef6 completed June 7, 2026, 6:03 a.m.
NED2 Entity disambiguation (via description) batch_6a250e036044819085e601b07f88a7ff completed June 7, 2026, 6:21 a.m.
Created at: April 17, 2026, 5:53 p.m.