Triple
T34513686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Angel |
E886090
|
entity |
| Predicate | announcesToCharacter |
P22045
|
FINISHED |
| Object | Prior Walter |
—
|
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: Prior Walter | Statement: [The Angel, announcesToCharacter, Prior Walter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: announcesToCharacter Context triple: [The Angel, announcesToCharacter, Prior Walter]
-
A.
announcedTo
chosen
Indicates that one entity formally communicated or made known some information, decision, or event to another specific entity.
-
B.
spokenToCharacter
Indicates that one character has verbally addressed or communicated directly with another character.
-
C.
publishesCharacter
Indicates that an entity (such as a publisher or platform) makes a character publicly available or officially releases that character.
-
D.
announcedThat
Indicates that one entity publicly communicated or declared a specific fact, decision, or piece of information about another entity or situation.
-
E.
announcedFor
Indicates that one entity has been publicly declared or made known in connection with, or on behalf 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_69f349ccc290819089d8e82698e53cb6 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71fb1ab3881908e2f7c0e6f23db49 |
completed | May 3, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 2:01 a.m.