Triple
T558629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen of Saint Lucia |
E13398
|
entity |
| Predicate | titleEndedWith |
P3587
|
FINISHED |
| Object | death of Elizabeth II |
—
|
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: death of Elizabeth II | Statement: [Queen of Saint Lucia, titleEndedWith, death of Elizabeth II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleEndedWith Context triple: [Queen of Saint Lucia, titleEndedWith, death of Elizabeth II]
-
A.
endedWith
chosen
Indicates that one event, process, or state concluded with or was finalized by another specified event, condition, or outcome.
-
B.
concludedBy
Indicates that an event, process, or state is brought to an end or finalized by a specific agent or entity.
-
C.
titleRetainedAfter
Indicates that an entity continues to hold or use the same title after a specified event or point in time.
-
D.
closingVerse
Indicates that one entity serves as the final or concluding verse of another entity, such as a song, poem, or hymn.
-
E.
lastAired
Indicates the most recent time or date on which something (typically a broadcast or episode) was shown or transmitted.
- 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.