Triple

T25070360
Position Surface form Disambiguated ID Type / Status
Subject Thom Gunn E627890 entity
Predicate notableWork P4 FINISHED
Object The Sense of Movement
"The Sense of Movement" is a 1957 poetry collection by Thom Gunn that explores themes of physicality, identity, and modern life in a characteristically controlled yet energetic style.
 E1664286 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: The Sense of Movement | Statement: [Thom Gunn, notableWork, The Sense of Movement]
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: The Sense of Movement
Triple: [Thom Gunn, notableWork, The Sense of Movement]
Generated description
"The Sense of Movement" is a 1957 poetry collection by Thom Gunn that explores themes of physicality, identity, and modern life in a characteristically controlled yet energetic style.

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_69e2ff2d71dc8190b4758e57d643cbe4 completed April 18, 2026, 3:49 a.m.
NER Named-entity recognition batch_69f45d13c684819085690724d772616e completed May 1, 2026, 7:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1048da88088190b2a2d923ef402c26 completed May 22, 2026, 12:15 p.m.
NEDg Description generation batch_6a104caaf8208190a092b8ffaa1d48f2 completed May 22, 2026, 12:31 p.m.
NED2 Entity disambiguation (via description) batch_6a104d107b088190aad51efff7bcef1e completed May 22, 2026, 12:33 p.m.
Created at: April 18, 2026, 6:10 a.m.