Triple

T24070441
Position Surface form Disambiguated ID Type / Status
Subject murder of Albert Snyder E596209 entity
Predicate hasAssociatedPerson P2308 FINISHED
Object tabloid photographer Tom Howard
Tom Howard was a tabloid photographer best known for secretly capturing the infamous 1928 electric-chair execution photograph of convicted murderer Ruth Snyder at Sing Sing Prison.
E1619306 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: tabloid photographer Tom Howard | Statement: [murder of Albert Snyder, hasAssociatedPerson, tabloid photographer Tom Howard]
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: tabloid photographer Tom Howard
Triple: [murder of Albert Snyder, hasAssociatedPerson, tabloid photographer Tom Howard]
Generated description
Tom Howard was a tabloid photographer best known for secretly capturing the infamous 1928 electric-chair execution photograph of convicted murderer Ruth Snyder at Sing Sing Prison.

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_69e288c25c008190850cf447940ab181 completed April 17, 2026, 7:23 p.m.
NER Named-entity recognition batch_69f1db17c99881909f97e858fb183d86 completed April 29, 2026, 10:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f966873488190bdf976c3cbb43cf3 completed May 21, 2026, 11:34 p.m.
NEDg Description generation batch_6a0f9767ddc081909f9cb49ec15c3ca0 completed May 21, 2026, 11:38 p.m.
NED2 Entity disambiguation (via description) batch_6a0f9c2334688190bae5d6f0f57ef036 completed May 21, 2026, 11:58 p.m.
Created at: April 17, 2026, 10:41 p.m.