Triple
T34500185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorincourt Castle |
E885728
|
entity |
| Predicate | firstAppearsInFormat |
P22610
|
FINISHED |
| Object | novel |
—
|
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: novel | Statement: [Dorincourt Castle, firstAppearsInFormat, novel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstAppearsInFormat Context triple: [Dorincourt Castle, firstAppearsInFormat, novel]
-
A.
firstReleaseFormat
chosen
Indicates the original medium or format in which something (such as a work or product) was first released.
-
B.
presentedInFormat
Indicates that something is expressed, delivered, or made available using a particular format or representation.
-
C.
debutInFormat
Indicates the event or context in which an entity makes its first appearance or participation in a specific format (e.g., medium, style, or version).
-
D.
firstAppearanceFor
Indicates that an entity marks the initial occurrence or debut of another entity within a given context or medium.
-
E.
firstAppearsAs
Indicates that an entity is introduced or shown in a particular form, role, or identity for the first time in a given context.
- 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_69f349cc0220819081f154c6964f4dc2 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fbe4a08190bfe65ebd141164e9 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 2:01 a.m.