Triple
T14690914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Come unto these yellow sands |
E345029
|
entity |
| Predicate | addresseeInFiction |
P99038
|
FINISHED |
| Object | shipwrecked characters |
—
|
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: shipwrecked characters | Statement: [Come unto these yellow sands, addresseeInFiction, shipwrecked characters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addresseeInFiction Context triple: [Come unto these yellow sands, addresseeInFiction, shipwrecked characters]
-
A.
addresseeOf
Indicates that one entity is the intended recipient or target audience of a communication, message, or expression from another entity.
-
B.
characterAddressed
Indicates that one character directs speech, communication, or attention specifically toward another character.
-
C.
fictionalCharacter
Indicates that one entity is a fictional character that appears within the narrative world of another entity (such as a work, series, or franchise).
-
D.
targetInFiction
chosen
Indicates that one entity is the target or subject of an action, focus, or effect within a fictional work or narrative context.
-
E.
addresseeDescription
Indicates that one entity provides a descriptive characterization or identifying information about the addressee of a communication or message.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb585d46c81908d6964130914cec4 |
completed | April 14, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69de6579fb7881909becc8f5822b39d4 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:28 a.m.