Triple
T31100290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosamund |
E792653
|
entity |
| Predicate | husbandAction |
P51768
|
FINISHED |
| Object | Alboin killed her father Cunimund |
—
|
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: Alboin killed her father Cunimund | Statement: [Rosamund, husbandAction, Alboin killed her father Cunimund]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: husbandAction Context triple: [Rosamund, husbandAction, Alboin killed her father Cunimund]
-
A.
spouseAction
chosen
Indicates that one person performs an action toward or on their spouse within the context of a marital relationship.
-
B.
husbandIsCompanionOf
Indicates that a husband serves as a companion to another person, typically his spouse, highlighting a close, supportive relationship.
-
C.
husbandStatus
Indicates that one person holds the social and/or legal role of husband in relation to another person.
-
D.
takenFromHusbandBy
Indicates that something previously belonging to a husband was removed or seized by another specified party.
-
E.
roleDuringHusbandBan
Indicates that an entity holds or performs a specific role during the period in which a husband is subject to a ban.
- 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_69f224cf157c81909e2d2bd88c9282c3 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69c234d648190a243fb2b107136a9 |
completed | May 3, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69f69665cd9c819088c388fc82fec42e |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 29, 2026, 9:03 p.m.