Triple
T5206140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Dreamer |
E117514
|
entity |
| Predicate | functionInPoem |
P58104
|
FINISHED |
| Object | mediator between Rood and audience |
—
|
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: mediator between Rood and audience | Statement: [the Dreamer, functionInPoem, mediator between Rood and audience]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionInPoem Context triple: [the Dreamer, functionInPoem, mediator between Rood and audience]
-
A.
functionInPsalter
Indicates the specific liturgical, structural, or thematic role that a psalm (or part of it) serves within the overall collection of the Psalter.
-
B.
functionInText
chosen
Indicates that a text segment serves a specific rhetorical or structural function within a larger text.
-
C.
readPoemAt
Indicates that an entity reads or performs a poem at a specific time, place, or event.
-
D.
poeticStructure
Indicates a relationship where one entity defines, embodies, or specifies the formal poetic organization (such as meter, rhyme scheme, or stanza pattern) used by another entity.
-
E.
textualFunction
Indicates a functional or structural role that a text segment serves within a larger document or discourse (e.g., title, caption, summary, instruction).
- 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_69bd4463dd3c81909966123f20b79d57 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7a490338819080481df79d3aae01 |
completed | March 20, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69bd77bb4e8c819094b5ac7cf61512f9 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:47 p.m.