Triple

T3720885
Position Surface form Disambiguated ID Type / Status
Subject Akedah E81633 entity
Predicate hasKeyMoment P14117 FINISHED
Object angel of the Lord stops Abraham LITERAL 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: angel of the Lord stops Abraham | Statement: [Akedah, hasKeyMoment, angel of the Lord stops Abraham]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasKeyMoment
Context triple: [Akedah, hasKeyMoment, angel of the Lord stops Abraham]
  • A. hasKeyDate
    Indicates a relationship where an entity is associated with an important or significant date relevant to its status, lifecycle, or context.
  • B. hasKeyActivity
    Indicates that an entity is associated with or performs a primary or central activity.
  • C. hasKeyWork
    Indicates that an entity possesses or is associated with a primary or central work (such as a main publication, artwork, or project) that is especially representative or important.
  • D. hasKeyAspect chosen
    Indicates that something possesses a central, defining, or particularly important feature or characteristic.
  • E. hasKeyPassage
    Indicates that one entity contains or includes a particularly important or central passage relevant to another entity.
  • F. None of above.

Provenance (3 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_69ad8b1b7ef081908d2d381bbf54985a completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adca9b5ca8819094299fffc02606ce completed March 8, 2026, 7:14 p.m.
PD Predicate disambiguation batch_69adc0436e508190909ec4a3e8443aef completed March 8, 2026, 6:30 p.m.
Created at: March 8, 2026, 3:34 p.m.