Triple

T27251584
Position Surface form Disambiguated ID Type / Status
Subject Helen Dunmore E687499 entity
Predicate notableWork P4 FINISHED
Object Talking to the Dead
"Talking to the Dead" is a psychological novel by Helen Dunmore that explores family secrets, memory, and grief through the tense relationship between two sisters reunited after a long estrangement.
 E1764397 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: Talking to the Dead | Statement: [Helen Dunmore, notableWork, Talking to the Dead]
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: Talking to the Dead
Triple: [Helen Dunmore, notableWork, Talking to the Dead]
Generated description
"Talking to the Dead" is a psychological novel by Helen Dunmore that explores family secrets, memory, and grief through the tense relationship between two sisters reunited after a long estrangement.

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_69ef35567e808190a94458cd44ebff0c completed April 27, 2026, 10:07 a.m.
NER Named-entity recognition batch_69f626b5b99081908d173630fade1f36 completed May 2, 2026, 4:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12627f71b08190930f5e94dd6d9b12 completed May 24, 2026, 2:29 a.m.
NEDg Description generation batch_6a126a21e65481908e3badc3d370b7af completed May 24, 2026, 3:01 a.m.
NED2 Entity disambiguation (via description) batch_6a126a826f588190953333802f314dfd completed May 24, 2026, 3:03 a.m.
Created at: April 27, 2026, 10:45 a.m.