Triple
T30415985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Her Grace |
E773756
|
entity |
| Predicate | usedInWrittenAddress |
P12836
|
FINISHED |
| Object | letters to duchesses |
—
|
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: letters to duchesses | Statement: [Her Grace, usedInWrittenAddress, letters to duchesses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInWrittenAddress Context triple: [Her Grace, usedInWrittenAddress, letters to duchesses]
-
A.
usedInStyleOfAddress
Indicates that one entity is used as a form or style of address when referring to or speaking to another entity.
-
B.
usesAddressTo
Indicates that one entity makes use of a particular address (such as a physical, email, or network address) to interact, communicate, or perform an action involving another entity.
-
C.
usesMailingAddressOf
Indicates that one entity uses another entity’s mailing address as its own for receiving mail or official correspondence.
-
D.
addressedWith
Indicates that one entity is referred to or spoken to using a particular name, title, or form of address.
-
E.
isStyleOfAddress
chosen
Indicates that one term or expression functions as a particular way of addressing or referring 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_69f22490b8b48190ab10c886a8d58c89 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd5d48855c8190bd93070b6a00d8b5 |
completed | May 8, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69fd5c9aabb88190912800d90184a89d |
completed | May 8, 2026, 3:46 a.m. |
Created at: April 29, 2026, 8:05 p.m.