Triple
T36806117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs Kitty Warren |
E909455
|
entity |
| Predicate | concealsInformation |
P177563
|
FINISHED |
| Object | true source of her income |
—
|
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: true source of her income | Statement: [Mrs Kitty Warren, concealsInformation, true source of her income]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: concealsInformation Context triple: [Mrs Kitty Warren, concealsInformation, true source of her income]
-
A.
concealability
Indicates the degree to which something can be hidden or kept from being noticed or discovered.
-
B.
usesHiddenInformation
Indicates that an entity relies on or exploits information that is not publicly known or observable to others in performing an action or making a decision.
-
C.
concealment
chosen
Indicates an action or state in which something is intentionally hidden, obscured, or kept from being seen or known by others.
-
D.
concealmentType
Indicates the specific manner or method by which something is hidden, obscured, or kept from detection.
-
E.
identityConcealedBy
Indicates that one entity hides, masks, or obscures the true identity 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_69f76e7cbbf48190891227b14d041139 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fbad1e94988190b86d447a68e65067 |
completed | May 6, 2026, 9:05 p.m. |
| PD | Predicate disambiguation | batch_69fba881b8e0819094790935152b99a1 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:13 p.m.