Triple

T29107086
Position Surface form Disambiguated ID Type / Status
Subject CASP14 E736788 entity
Predicate isSubEventOf P6285 FINISHED
Object CASP series of experiments
The CASP series of experiments is a long-running community-wide initiative in computational biology that regularly evaluates and benchmarks methods for predicting protein structures.
 E1849478 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: CASP series of experiments | Statement: [CASP14, isSubEventOf, CASP series of experiments]
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: CASP series of experiments
Triple: [CASP14, isSubEventOf, CASP series of experiments]
Generated description
The CASP series of experiments is a long-running community-wide initiative in computational biology that regularly evaluates and benchmarks methods for predicting protein structures.

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_69f077ec765c81909474c88bcc8bab43 completed April 28, 2026, 9:03 a.m.
NER Named-entity recognition batch_69f661bb81b481909690f8617a84cb19 completed May 2, 2026, 8:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2537c079688190b8142efa06575188 completed June 7, 2026, 9:20 a.m.
NEDg Description generation batch_6a253bde7d1c819082d2aeac0b835460 completed June 7, 2026, 9:37 a.m.
NED2 Entity disambiguation (via description) batch_6a253fc091b8819091f9253f88e27df4 completed June 7, 2026, 9:54 a.m.
Created at: April 28, 2026, 11:16 a.m.