Triple
T33113056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Sindarin |
E847379
|
entity |
| Predicate | spokenInFiction |
P161980
|
FINISHED |
| Object | Beleriand (northern regions) |
—
|
NE NERFINISHED |
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: Beleriand (northern regions) | Statement: [North Sindarin, spokenInFiction, Beleriand (northern regions)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spokenInFiction Context triple: [North Sindarin, spokenInFiction, Beleriand (northern regions)]
-
A.
spokenInFictionalLocation
chosen
Indicates that a language, dialogue, or speech is used or occurs within a fictional or imaginary location.
-
B.
speaksInFilm
Indicates that a person or character provides spoken dialogue or voice work within a particular film.
-
C.
spokenBy
Indicates that a particular utterance, statement, or piece of speech is produced or said by a specific entity.
-
D.
spokenOfAs
Indicates that one entity is referred to, characterized, or talked about in a particular way by another entity or within a given context.
-
E.
spokenToCharacter
Indicates that one character has verbally addressed or communicated directly with another character.
- 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_69f3495751a081909850af5843da40dc |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6db6af1d88190989810182354d60f |
completed | May 3, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_69f6d82d068c8190940a3200ed760e38 |
completed | May 3, 2026, 5:07 a.m. |
Created at: May 1, 2026, 1:27 a.m.