Triple
T25772373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Verse of the Throne |
E649053
|
entity |
| Predicate | oftenRecitedBefore |
P112504
|
FINISHED |
| Object | sleep |
—
|
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: sleep | Statement: [Verse of the Throne, oftenRecitedBefore, sleep]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenRecitedBefore Context triple: [Verse of the Throne, oftenRecitedBefore, sleep]
-
A.
isOftenRecitedFor
chosen
Indicates that something (such as a text, phrase, or piece of music) is frequently spoken, chanted, or performed for a particular purpose, audience, or occasion.
-
B.
mayBeRecited
Indicates that something is permitted or suitable to be spoken aloud or recited, typically in a formal or ritualized manner.
-
C.
recitedOnOccasion
Indicates that something (typically a text, speech, or performance) was recited during or in connection with a specific occasion or event.
-
D.
recites
Indicates that one entity verbally delivers or repeats from memory the words, text, or performance associated with another entity.
-
E.
oftenSays
Indicates that one entity frequently makes a particular statement or remark, or regularly expresses a certain idea or phrase.
- 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_69e7ab333b508190b6d708d8d9a328ed |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
Created at: April 22, 2026, 5:31 a.m.