Triple
T28518895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calla Bryn Sturgis |
E721701
|
entity |
| Predicate | subjectOfEvent |
P177130
|
FINISHED |
| Object | raids by the Wolves |
—
|
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: raids by the Wolves | Statement: [Calla Bryn Sturgis, subjectOfEvent, raids by the Wolves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectOfEvent Context triple: [Calla Bryn Sturgis, subjectOfEvent, raids by the Wolves]
-
A.
immediateSubjectOf
Indicates that one entity is the direct grammatical subject of another entity (typically a clause, phrase, or verb), without any intervening subject relations.
-
B.
subjectOfDescription
Indicates that the subject is the main entity being described or characterized in a given context or statement.
-
C.
subjectOfIntroduction
Indicates that one entity is the topic or focus being introduced by another entity.
-
D.
subjectOfOperation
Indicates that an entity is the primary focus, target, or object upon which an operation or procedure is performed.
-
E.
fieldOfEvent
Indicates the domain, discipline, or area of activity within which an event takes place or is categorized.
- 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_69f01a5cbcc4819083fb4e723378713e |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6f85bfba48190aba95b40642a8ca7 |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69f6f854486c81909396d944a55e03ab |
completed | May 3, 2026, 7:25 a.m. |
Created at: April 28, 2026, 3:19 a.m.