Triple

T24746130
Position Surface form Disambiguated ID Type / Status
Subject Ted Chiang E618703 entity
Predicate notableWork P4 FINISHED
Object Seventy-Two Letters
Seventy-Two Letters is a science fiction novella by Ted Chiang that blends kabbalistic mysticism with alternate-history science to explore language, identity, and the nature of creation.
 E1654426 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: Seventy-Two Letters | Statement: [Ted Chiang, notableWork, Seventy-Two Letters]
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: Seventy-Two Letters
Triple: [Ted Chiang, notableWork, Seventy-Two Letters]
Generated description
Seventy-Two Letters is a science fiction novella by Ted Chiang that blends kabbalistic mysticism with alternate-history science to explore language, identity, and the nature of creation.

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_69e2fab8f95c81908bb9e552cf3280c2 completed April 18, 2026, 3:30 a.m.
NER Named-entity recognition batch_69f4105a49388190a04307aad25b07e9 completed May 1, 2026, 2:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a101c030a9c81909368f2986bec3742 completed May 22, 2026, 9:04 a.m.
NEDg Description generation batch_6a1028143b4c8190b89ad73aecb56e0d completed May 22, 2026, 9:55 a.m.
NED2 Entity disambiguation (via description) batch_6a1029a084708190a87c7d2add8f4688 completed May 22, 2026, 10:02 a.m.
Created at: April 18, 2026, 4:21 a.m.