Triple

T34251688
Position Surface form Disambiguated ID Type / Status
Subject Peter Matthiessen E878762 entity
Predicate notableWork P4 FINISHED
Object Lost Man’s River
Lost Man’s River is a historical novel by Peter Matthiessen that explores the violent, enigmatic past of Florida’s Everglades through the investigation of a murdered outlaw.
 E2087116 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: Lost Man’s River | Statement: [Peter Matthiessen, notableWork, Lost Man’s River]
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: Lost Man’s River
Triple: [Peter Matthiessen, notableWork, Lost Man’s River]
Generated description
Lost Man’s River is a historical novel by Peter Matthiessen that explores the violent, enigmatic past of Florida’s Everglades through the investigation of a murdered outlaw.

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_69f349b3618481909df955b063f305b2 completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69f712a2370c8190854b9d5e5541f7c7 completed May 3, 2026, 9:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a36d5f40e6481909a9cc472bb6bc01c completed June 20, 2026, 6:03 p.m.
NEDg Description generation batch_6a36d69820ac8190a102919d7bfbbeeb completed June 20, 2026, 6:06 p.m.
NED2 Entity disambiguation (via description) batch_6a36d733c79c819099c6c8306ac9a7bd completed June 20, 2026, 6:08 p.m.
Created at: May 1, 2026, 1:56 a.m.