Triple
T32113612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guard of the Citadel |
E820179
|
entity |
| Predicate | oathFormulaIncludes |
P65553
|
FINISHED |
| Object | "Here do I swear fealty and service" |
—
|
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: "Here do I swear fealty and service" | Statement: [Guard of the Citadel, oathFormulaIncludes, "Here do I swear fealty and service"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oathFormulaIncludes Context triple: [Guard of the Citadel, oathFormulaIncludes, "Here do I swear fealty and service"]
-
A.
containsOathBy
Indicates that one entity (such as a text, document, or statement) includes or features an oath made by another entity.
-
B.
oath
Indicates a formal, binding promise or pledge made by one party to uphold certain duties, truths, or obligations, often under conditions of solemnity or authority.
-
C.
hasOathTo
Indicates a relationship in which one entity is bound by an oath or sworn commitment to another entity.
-
D.
oathTextDefinedIn
chosen
Indicates that the specific wording or content of an oath is defined or specified within a particular document, source, or context.
-
E.
oathsAbout
Indicates that one entity makes or concerns a formal oath regarding another entity or subject.
- 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_69f3490209c881908ec0241476715f15 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b906a92c819096335394dd7f767e |
completed | May 3, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a970b0819090c6473844ffa8e3 |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:27 a.m.