Triple
T38010993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs. Bardell |
E948362
|
entity |
| Predicate | believesSheIsEngagedTo |
P189854
|
FINISHED |
| Object | Samuel Pickwick |
—
|
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: Samuel Pickwick | Statement: [Mrs. Bardell, believesSheIsEngagedTo, Samuel Pickwick]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: believesSheIsEngagedTo Context triple: [Mrs. Bardell, believesSheIsEngagedTo, Samuel Pickwick]
-
A.
engagedTo
Indicates that two entities are formally committed to marry each other.
-
B.
secretlyEngagedTo
Indicates that one person is engaged to marry another, but this engagement is intentionally kept hidden from others.
-
C.
engagedOn
Indicates that two entities are committed to be married to each other as of a specific date or point in time.
-
D.
engagedBy
Indicates that an entity is actively involved, occupied, or participating in an activity, process, or interaction initiated or provided by another entity.
-
E.
proposedBride
Indicates that one entity has been put forward or suggested as a potential bride for another entity.
- F. None of above. chosen
Provenance (4 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_69f76efb4b10819092c8c2ba28ac06a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbca6c066c8190a1599202f341417f |
completed | May 6, 2026, 11:10 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
| PDg | Predicate description generation | batch_69fbc993caa881908c16c3e21efaeef9 |
completed | May 6, 2026, 11:07 p.m. |
Created at: May 3, 2026, 4:20 p.m.