Triple

T21527392
Position Surface form Disambiguated ID Type / Status
Subject Calm with Horses E531130 entity
Predicate character P662 FINISHED
Object Dymphna Devers
Dymphna Devers is a character in the Irish crime drama film "Calm with Horses," involved in the tense, violent world surrounding the Devers crime family.
E1683935 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: Dymphna Devers | Statement: [Calm with Horses, character, Dymphna Devers]
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: Dymphna Devers
Triple: [Calm with Horses, character, Dymphna Devers]
Generated description
Dymphna Devers is a character in the Irish crime drama film "Calm with Horses," involved in the tense, violent world surrounding the Devers crime family.

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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee88522e948190b9fa5a3587f32eae completed April 26, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10ad18b43c8190bd2eb11a39566ed1 completed May 22, 2026, 7:23 p.m.
NEDg Description generation batch_6a10adf21b3c8190a7388b1a74faf65e completed May 22, 2026, 7:26 p.m.
NED2 Entity disambiguation (via description) batch_6a10af62078481908759f9df2167d81f completed May 22, 2026, 7:32 p.m.
Created at: April 16, 2026, 6:26 p.m.