Triple

T27074867
Position Surface form Disambiguated ID Type / Status
Subject Frank Cashen E685429 entity
Predicate fullName P16 FINISHED
Object John Francis Cashen
John Francis Cashen, better known as Frank Cashen, was an American baseball executive most recognized for building the New York Mets into a World Series–winning team in the 1980s.
 E1754878 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: John Francis Cashen | Statement: [Frank Cashen, fullName, John Francis Cashen]
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: John Francis Cashen
Triple: [Frank Cashen, fullName, John Francis Cashen]
Generated description
John Francis Cashen, better known as Frank Cashen, was an American baseball executive most recognized for building the New York Mets into a World Series–winning team in the 1980s.

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_69ef14843b1481909d828b3d5a44550a completed April 27, 2026, 7:47 a.m.
NER Named-entity recognition batch_69f62314899c8190a8d6c7175efc2dec completed May 2, 2026, 4:15 p.m.
NED1 Entity disambiguation (via context triple) batch_6a123adc34708190850f196753e14cdb completed May 23, 2026, 11:40 p.m.
NEDg Description generation batch_6a123c648380819097286e21852bb099 completed May 23, 2026, 11:46 p.m.
NED2 Entity disambiguation (via description) batch_6a123cc57c1481909a74a261af71a2c2 completed May 23, 2026, 11:48 p.m.
Created at: April 27, 2026, 8:30 a.m.