Triple
T24539679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erzherzogin von Österreich |
E607055
|
entity |
| Predicate | rankRelativeToKing |
P156652
|
FINISHED |
| Object | above Duchess |
—
|
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: above Duchess | Statement: [Erzherzogin von Österreich, rankRelativeToKing, above Duchess]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankRelativeToKing Context triple: [Erzherzogin von Österreich, rankRelativeToKing, above Duchess]
-
A.
positionOnKing
Indicates that one entity occupies a specific positional relationship relative to a king in a given context.
-
B.
evaluatesKingsBy
Indicates a relationship where an agent assesses or judges kings according to a specified criterion, standard, or method.
-
C.
opponentKing
Indicates that one entity is the king belonging to the opposing or rival side of the other entity.
-
D.
kingIsInviolable
Indicates that the king is protected from harm, violation, or infringement, often implying legal or moral immunity from certain actions.
-
E.
rankBeforeKingship
Indicates that one entity held a higher or earlier rank or status than another entity prior to that other entity attaining kingship.
- F. None of above. chosen
Provenance (4 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_69e2c4c9bf94819082d05da6f5c29907 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
| PDg | Predicate description generation | batch_69f2b8b8bc5881908df49c0b07110246 |
completed | April 30, 2026, 2:04 a.m. |
Created at: April 18, 2026, 2:26 a.m.