Triple

T29704028
Position Surface form Disambiguated ID Type / Status
Subject Clark Ashton Smith E751575 entity
Predicate notableWork P4 FINISHED
Object The Double Shadow
"The Double Shadow" is a dark fantasy and horror short story by Clark Ashton Smith, noted for its rich, atmospheric prose and themes of forbidden magic and cosmic dread.
E1878764 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 Double Shadow | Statement: [Clark Ashton Smith, notableWork, The Double Shadow]
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 Double Shadow
Triple: [Clark Ashton Smith, notableWork, The Double Shadow]
Generated description
"The Double Shadow" is a dark fantasy and horror short story by Clark Ashton Smith, noted for its rich, atmospheric prose and themes of forbidden magic and cosmic dread.

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_69f0d6266f8481909e70bb41cda18587 completed April 28, 2026, 3:45 p.m.
NER Named-entity recognition batch_69f672b6ba408190a02e828fd1b62df7 completed May 2, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_6a267ed6505081909fbbd29678211426 completed June 8, 2026, 8:35 a.m.
NEDg Description generation batch_6a2682b7ceb8819081d1c84a1e19b7c4 completed June 8, 2026, 8:52 a.m.
NED2 Entity disambiguation (via description) batch_6a2686b922f0819081985e4d6c5a0f2e completed June 8, 2026, 9:09 a.m.
Created at: April 28, 2026, 7:26 p.m.