Triple
T558613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen of Saint Lucia |
E13398
|
entity |
| Predicate | monarchTo |
P7969
|
FINISHED |
| Object | 2022-09-08 |
—
|
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: 2022-09-08 | Statement: [Queen of Saint Lucia, monarchTo, 2022-09-08]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: monarchTo Context triple: [Queen of Saint Lucia, monarchTo, 2022-09-08]
-
A.
monarch
Indicates that an entity serves as the sovereign ruler (such as a king, queen, or emperor) over a state or territory.
-
B.
monarchUntil
chosen
Indicates that an entity served as monarch over another entity up to, but not beyond, a specified end time or event.
-
C.
monarchRole
Indicates that an entity holds or is assigned the role, office, or position of a monarch in relation to a state or domain.
-
D.
monarchAtStart
Indicates that the referenced entity was the reigning monarch at the beginning of a specified period, event, or sequence.
-
E.
monarchNumber
Indicates the ordinal position or sequence number assigned to a monarch within a line of rulers.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a499df43f08190b514a38d36fc271d |
completed | March 1, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69a494bd78e8819083c519669158f209 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.