Triple
T20775011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inkdeath |
E511332
|
entity |
| Predicate | languageMagicConcept |
P133787
|
FINISHED |
| Object | reading characters out of books |
—
|
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: reading characters out of books | Statement: [Inkdeath, languageMagicConcept, reading characters out of books]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageMagicConcept Context triple: [Inkdeath, languageMagicConcept, reading characters out of books]
-
A.
conceptualMeaning
Indicates the abstract idea, concept, or underlying significance that something represents or conveys.
-
B.
languageTerm
Indicates that one entity is a linguistic expression (word, phrase, or term) used to denote or label the other entity.
-
C.
objectMeaning
Indicates that one entity represents, expresses, or conveys the meaning or semantic content of another entity.
-
D.
magicWord
Indicates that an entity is a special word or phrase that, when used, triggers a particular effect, action, or access.
-
E.
fictionalConceptFrom
chosen
Indicates that a fictional concept originates from, is introduced in, or is derived from a particular source or work.
- 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_69e0b4cac7a48190a715cb3d545df2b4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c26a39bc81909ca5d102056d8586 |
completed | April 21, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:37 p.m.