Triple
T37795435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Song of Amergin |
E942192
|
entity |
| Predicate | characterSpeaks |
P196082
|
FINISHED |
| Object | Amergin Glúingel |
—
|
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: Amergin Glúingel | Statement: [Song of Amergin, characterSpeaks, Amergin Glúingel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterSpeaks Context triple: [Song of Amergin, characterSpeaks, Amergin Glúingel]
-
A.
spokenToCharacter
Indicates that one character has verbally addressed or communicated directly with another character.
-
B.
character1
Indicates that the subject is identified as the first or primary character in a narrative or context.
-
C.
hasCharacterMonologue
Indicates that a character delivers an extended solo speech or monologue within a narrative or performance.
-
D.
speaksWith
Indicates that one entity engages in spoken communication or conversation with another entity.
-
E.
hasFictionalSpeaker
chosen
Indicates that a work, text, or expression is presented as being spoken by an invented or non-real speaker rather than an actual person.
- 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_69f76ee6f1f4819091e2cf9c9e6aee19 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a000014497c819088d5cda3977522dd |
completed | May 10, 2026, 3:48 a.m. |
| PD | Predicate disambiguation | batch_69ffff9a52b08190be1024e0fb6fe661 |
completed | May 10, 2026, 3:46 a.m. |
Created at: May 3, 2026, 4:19 p.m.