Triple
T26759807
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adèle Varens |
E674768
|
entity |
| Predicate | wardStatus |
P21208
|
FINISHED |
| Object | ward of Mr. Rochester |
—
|
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: ward of Mr. Rochester | Statement: [Adèle Varens, wardStatus, ward of Mr. Rochester]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wardStatus Context triple: [Adèle Varens, wardStatus, ward of Mr. Rochester]
-
A.
wardNumber
Indicates the specific ward identifier or number associated with an entity, typically within an institution like a hospital or electoral district.
-
B.
ward
chosen
Indicates that one entity is under the protection, guardianship, or custodial responsibility of another entity.
-
C.
status
Indicates the current condition, state, or standing of an entity within a given context.
-
D.
laterStatus
Indicates that one entity represents a subsequent or resulting status or condition of another entity in time.
-
E.
enteredStatus
Indicates that an entity has transitioned into or assumed a particular status or state.
- 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_69eecda6e9dc81908452fab3ba17ed9b |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f618dafb6c8190b4f53a7fcbf967e3 |
completed | May 2, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:57 a.m.