Triple
T38399481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rock of Dunamase |
E900855
|
entity |
| Predicate | grantedAsDowryOf |
P53463
|
FINISHED |
| Object | Aoife MacMurrough |
—
|
NE NERFINISHED |
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: Aoife MacMurrough | Statement: [Rock of Dunamase, grantedAsDowryOf, Aoife MacMurrough]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grantedAsDowryOf Context triple: [Rock of Dunamase, grantedAsDowryOf, Aoife MacMurrough]
-
A.
broughtAsDowryTo
Indicates that one entity was transferred as dowry to another entity, typically as part of a marriage arrangement.
-
B.
grantedAsDowerTo
chosen
Indicates that something (typically property or rights) is given to a person as dower, i.e., as a legal provision or settlement made upon marriage or upon a spouse’s death.
-
C.
dowry
Indicates the transfer of wealth or property from a bride’s family to the groom or his family as part of a marriage arrangement.
-
D.
receivedAsWifeFrom
Indicates that one entity was given or transferred to another entity specifically in the role or status of a wife.
-
E.
marriedToHeiress
Indicates that a person is married to someone who is an heiress.
- 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_69f76e6071a081909eea7a670d21420c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd474b7e788190a9bb9b542d878f60 |
completed | May 8, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69fd46d8b2f0819099d92d72c902f60e |
completed | May 8, 2026, 2:13 a.m. |
Created at: May 3, 2026, 4:31 p.m.