Triple

T27930631
Position Surface form Disambiguated ID Type / Status
Subject Su Shi E707968 entity
Predicate notableWork P4 FINISHED
Object Later Ode on the Red Cliff
Later Ode on the Red Cliff is a prose-poem by the Song dynasty writer Su Shi that reflects on transience, friendship, and nature during a second visit to the historic Red Cliff site.
 E1798681 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: Later Ode on the Red Cliff | Statement: [Su Shi, notableWork, Later Ode on the Red Cliff]
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: Later Ode on the Red Cliff
Triple: [Su Shi, notableWork, Later Ode on the Red Cliff]
Generated description
Later Ode on the Red Cliff is a prose-poem by the Song dynasty writer Su Shi that reflects on transience, friendship, and nature during a second visit to the historic Red Cliff site.

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_69ef96bbf2c48190a9d0e0291457aab6 completed April 27, 2026, 5:02 p.m.
NER Named-entity recognition batch_69f63a9c5a448190b739a79523610bfd completed May 2, 2026, 5:55 p.m.
NED1 Entity disambiguation (via context triple) batch_6a15b8851fa081909c418b547d1b1492 completed May 26, 2026, 3:13 p.m.
NEDg Description generation batch_6a15b97876388190882b42942fc86c3c completed May 26, 2026, 3:17 p.m.
NED2 Entity disambiguation (via description) batch_6a15ba15ed6481908eadd24fa99efccf completed May 26, 2026, 3:19 p.m.
Created at: April 27, 2026, 7:02 p.m.