Triple

T31370015
Position Surface form Disambiguated ID Type / Status
Subject Sam Cutler E800133 entity
Predicate birthName P65 FINISHED
Object Brendan Lawrence Lyons
Brendan Lawrence Lyons is the birth name of Sam Cutler, the British rock tour manager best known for working with the Rolling Stones and the Grateful Dead.
 E1959337 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: Brendan Lawrence Lyons | Statement: [Sam Cutler, birthName, Brendan Lawrence Lyons]
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: Brendan Lawrence Lyons
Triple: [Sam Cutler, birthName, Brendan Lawrence Lyons]
Generated description
Brendan Lawrence Lyons is the birth name of Sam Cutler, the British rock tour manager best known for working with the Rolling Stones and the Grateful Dead.

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_69f224e6b7448190ac6bf97ad7364160 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f69f88eaec8190b96595465b7fa83e completed May 3, 2026, 1:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2a722db15881908ebdc3e8826fb547 completed June 11, 2026, 8:30 a.m.
NEDg Description generation batch_6a2a729237148190ae28589b9a1665d7 completed June 11, 2026, 8:32 a.m.
NED2 Entity disambiguation (via description) batch_6a2a9e880bb48190875742fff1c69701 completed June 11, 2026, 11:39 a.m.
Created at: April 29, 2026, 9:18 p.m.