Triple
T32192724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romney Wordsworth |
E822304
|
entity |
| Predicate | chargesByRegime |
P26388
|
FINISHED |
| Object | being a librarian |
—
|
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: being a librarian | Statement: [Romney Wordsworth, chargesByRegime, being a librarian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chargesByRegime Context triple: [Romney Wordsworth, chargesByRegime, being a librarian]
-
A.
chargeType
Indicates the category or nature of a charge applied in a transaction or interaction between entities (e.g., fee type, billing classification, or legal charge type).
-
B.
chargesBasedOn
Indicates that one party determines or applies a fee, price, or cost to another party or item according to a specified basis, criterion, or reference.
-
C.
chargeBasis
Indicates the underlying reason, justification, or legal/contractual basis on which a charge, fee, or accusation is applied.
-
D.
chargesVia
Indicates that one entity charges or powers another entity using a specified medium, method, or interface.
-
E.
taxRegime
chosen
Indicates the system or structure of taxation that governs how taxes are assessed, collected, and applied within a particular context or jurisdiction.
- 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_69f3490819cc81909bae1f8ce99423c5 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bace6c508190a7b25ad1024151b6 |
completed | May 3, 2026, 3:02 a.m. |
| PD | Predicate disambiguation | batch_69f6b6293188819080d5041ca0adb969 |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:35 a.m.