Triple
T36821487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kitty Kiernan |
E909895
|
entity |
| Predicate | hasWorkAddressedToHer |
P126591
|
FINISHED |
| Object | letters of Michael Collins |
—
|
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 of Michael Collins | Statement: [Kitty Kiernan, hasWorkAddressedToHer, letters of Michael Collins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkAddressedToHer Context triple: [Kitty Kiernan, hasWorkAddressedToHer, letters of Michael Collins]
-
A.
addressedBefore
Indicates that one entity was addressed or spoken to prior to another entity in time.
-
B.
wasAddressedAs
Indicates that one entity referred to or called another entity by a particular name, title, or form of address.
-
C.
addressedFor
chosen
Indicates that something is directed, designated, or intended for a particular recipient or target.
-
D.
addressedBy
Indicates that something (such as an issue, request, or item) is handled, dealt with, or responded to by a particular agent or entity.
-
E.
addressedWith
Indicates that one entity is referred to or spoken to using a particular name, title, or form of address.
- 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_69f76e7dd13c81908c60b05adb49eeb5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fecd0a732c819097bdd3eb69b6158c |
completed | May 9, 2026, 5:58 a.m. |
| PD | Predicate disambiguation | batch_69fecc0318d481908b5b20598a76a9fe |
completed | May 9, 2026, 5:54 a.m. |
Created at: May 3, 2026, 4:13 p.m.