Triple

T35051162
Position Surface form Disambiguated ID Type / Status
Subject Blades E1011331 entity
Predicate notableActivityInOblivion P129177 FINISHED
Object protecting Martin Septim 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: protecting Martin Septim | Statement: [Blades, notableActivityInOblivion, protecting Martin Septim]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: notableActivityInOblivion
Context triple: [Blades, notableActivityInOblivion, protecting Martin Septim]
  • A. notableActivityIn chosen
    Indicates that an entity is particularly recognized for performing a significant activity within a specified place, context, or domain.
  • B. notableActionAt
    Indicates that an entity performed or was involved in a significant action or event at a specific location or point in time.
  • C. notableBuildingActivity
    Indicates that an entity is significantly involved in a noteworthy construction, renovation, or development activity related to a building or structure.
  • D. notableDeed
    Indicates that an entity is recognized for performing a significant or noteworthy action or achievement.
  • E. notableYearOfActivity
    Indicates the specific year during which an entity was particularly active, prominent, or notable in its activities or impact.
  • 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_69f76dcfdda48190b1ebae5da8b54f12 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_6a037c8c34f88190ace26f555827f23e completed May 12, 2026, 7:16 p.m.
PD Predicate disambiguation batch_6a037a016960819093ed4990fb4d9d36 completed May 12, 2026, 7:05 p.m.
Created at: May 3, 2026, 4:01 p.m.