Triple
T11046943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beren and Lúthien |
E261158
|
entity |
| Predicate | isToldThrough |
P79220
|
FINISHED |
| Object | multiple textual versions |
—
|
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: multiple textual versions | Statement: [Beren and Lúthien, isToldThrough, multiple textual versions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isToldThrough Context triple: [Beren and Lúthien, isToldThrough, multiple textual versions]
-
A.
modeOfTelling
chosen
Indicates the manner or medium through which something is narrated, communicated, or expressed.
-
B.
narratedTo
Indicates that one entity tells or recounts a story, event, or information directly to another entity as the audience.
-
C.
narratedFrom
Indicates that an event, story, or account is told or described from the perspective or vantage point of a particular source or narrator.
-
D.
isNarrativeDriven
Indicates that an entity’s primary structure or progression is guided by a storyline or plot rather than by mechanics, data, or other non-story elements.
-
E.
containsNarrativeOf
Indicates that one entity includes or presents the story, account, or narrative content of another entity.
- 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_69d6aa979bdc8190bf0e79104cc098c1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798307da481908996557a73c9b49a |
completed | April 9, 2026, 12:14 p.m. |
| PD | Predicate disambiguation | batch_69d74407cb088190ba37c8da3d342b64 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.