Triple
T408988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Barbara |
E9444
|
entity |
| Predicate | legend |
P11062
|
FINISHED |
| Object | kept in a tower by her pagan father |
—
|
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: kept in a tower by her pagan father | Statement: [Saint Barbara, legend, kept in a tower by her pagan father]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legend Context triple: [Saint Barbara, legend, kept in a tower by her pagan father]
-
A.
lays
Indicates that one entity deposits or places something, typically eggs or objects, onto a surface or in a location.
-
B.
title
Indicates that one entity serves as the formal name or designation of another entity.
-
C.
flag
Indicates that one entity marks, signals, or draws attention to another entity, often to denote status, importance, or the need for review or action.
-
D.
badge
Indicates that one entity confers, displays, or is associated with a symbolic mark or emblem representing status, achievement, role, or affiliation in relation to another entity.
-
E.
legacyGoal
Indicates that an entity has a long-term, enduring objective or impact it aims to leave behind beyond its immediate actions or existence.
- F. None of above. chosen
Provenance (4 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ecc098c4819088d127c5ea55ced9 |
completed | Feb. 28, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69a2e971a3a481909e6b075f25dd234a |
completed | Feb. 28, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69a2ea4545608190898436c72e10f39d |
completed | Feb. 28, 2026, 1:14 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.