Triple
T33600444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Lady of Maryland |
E860701
|
entity |
| Predicate | usuallyUnpaid |
P145117
|
FINISHED |
| Object | true |
—
|
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 | Statement: [First Lady of Maryland, usuallyUnpaid, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usuallyUnpaid Context triple: [First Lady of Maryland, usuallyUnpaid, true]
-
A.
isUnpaid
Indicates that an expected payment, fee, or financial obligation has not yet been made or settled.
-
B.
isUnpaidOffice
chosen
Indicates that an office or position is held without financial compensation or salary.
-
C.
notChargedOn
Indicates that no financial charge or cost has been applied to a specified entity in relation to another entity or context.
-
D.
openLate
Indicates that a place or service remains open until a relatively late time compared to typical closing hours.
-
E.
unfinishedBy
Indicates that one entity has started but not completed an action, task, or process in relation to 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_69f3497f35908190a2e9bbb9b96c7a3f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f7aa07a48190b831b21bfb061db1 |
completed | May 3, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:41 a.m.