Triple
T4557895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard Talbot, 1st Earl of Tyrconnell |
E120522
|
entity |
| Predicate | createdEarlIn |
P55816
|
FINISHED |
| Object | 1685 |
—
|
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: 1685 | Statement: [Richard Talbot, 1st Earl of Tyrconnell, createdEarlIn, 1685]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdEarlIn Context triple: [Richard Talbot, 1st Earl of Tyrconnell, createdEarlIn, 1685]
-
A.
createdEarlBy
Indicates that an entity was granted or established as an earl by a specific creator or authority.
-
B.
earlTitleCreatedFor
chosen
Indicates that an earl title was specifically established or granted for a particular person or entity.
-
C.
createdIn
Indicates that one entity was brought into existence, produced, or originated within the context, location, or time frame specified by another entity.
-
D.
createdAfterEvent
Indicates that the creation of one entity occurred after a specified event in time.
-
E.
createdAround
Indicates that something was brought into existence or produced approximately at a particular time or within an imprecise time period.
- 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_69bd4636f1648190a701445c2fcd9c17 |
completed | March 20, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69bd58163e6081909d5a3aae12c42a00 |
completed | March 20, 2026, 2:22 p.m. |
| PD | Predicate disambiguation | batch_69bd52254c648190a5144cfe8fa7e409 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:09 p.m.