Triple

T24677882
Position Surface form Disambiguated ID Type / Status
Subject Book of Purity E611040 entity
Predicate hasPart P35 FINISHED
Object Laws of Vessels
Laws of Vessels is a section of Jewish ritual law that details how various types of containers and utensils contract and transmit impurity and how they can be purified.
E1645326 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: Laws of Vessels | Statement: [Book of Purity, hasPart, Laws of Vessels]
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: Laws of Vessels
Triple: [Book of Purity, hasPart, Laws of Vessels]
Generated description
Laws of Vessels is a section of Jewish ritual law that details how various types of containers and utensils contract and transmit impurity and how they can be purified.

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_69e2c4d5c2dc8190ac857dea25ec6ce9 completed April 17, 2026, 11:40 p.m.
NER Named-entity recognition batch_69f40fb0b500819082a6f2255a60835b completed May 1, 2026, 2:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1004ab304881908a4a8617c1bc9f63 completed May 22, 2026, 7:24 a.m.
NEDg Description generation batch_6a10079f208c81908f5683ebb2401950 completed May 22, 2026, 7:37 a.m.
NED2 Entity disambiguation (via description) batch_6a100857ceec81909d4a9169cb7cafe3 completed May 22, 2026, 7:40 a.m.
Created at: April 18, 2026, 3:07 a.m.