Triple
T21004094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wulf and Eadwacer |
E517368
|
entity |
| Predicate | speakerSituation |
P115376
|
FINISHED |
| Object | woman separated from her lover |
—
|
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: woman separated from her lover | Statement: [Wulf and Eadwacer, speakerSituation, woman separated from her lover]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speakerSituation Context triple: [Wulf and Eadwacer, speakerSituation, woman separated from her lover]
-
A.
snapSituation
Indicates a situation or context in which a sudden, decisive, or snapshot-like event or state occurs between entities.
-
B.
narrativeSituation
Indicates the contextual relationship that defines how events, characters, and perspectives are arranged and presented within a narrative.
-
C.
situationType
chosen
Indicates the general kind or category of situation, event, or circumstance that a given instance represents.
-
D.
sociolinguisticSituation
Indicates the social and cultural context in which language is used, including factors like participants, setting, norms, and power relations that shape linguistic behavior.
-
E.
refersSituationTo
Indicates that one entity directs or assigns a situation, case, or matter to another entity for attention, handling, or further action.
- 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_69e0b50192308190a284fcc89dd23a49 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc3978b0819082b63a98962a673e |
completed | April 21, 2026, 4:25 a.m. |
| PD | Predicate disambiguation | batch_69e5dbec80708190a49bccab7ff97e7b |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:52 p.m.