Triple
T31495580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rose Dawson Calvert |
E803530
|
entity |
| Predicate | throwsObjectIntoSea |
P26047
|
FINISHED |
| Object | Heart of the Ocean necklace |
—
|
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: Heart of the Ocean necklace | Statement: [Rose Dawson Calvert, throwsObjectIntoSea, Heart of the Ocean necklace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: throwsObjectIntoSea Context triple: [Rose Dawson Calvert, throwsObjectIntoSea, Heart of the Ocean necklace]
-
A.
castIntoSeaBy
chosen
Indicates that one entity causes another entity to be thrown or sent into the sea.
-
B.
castIntoSeaIn
Indicates that an entity is thrown or cast into a particular sea or body of seawater at a specified location or context.
-
C.
throws
Indicates that one entity propels or hurls another entity or object through space, typically by a deliberate physical action.
-
D.
thrownThrough
Indicates that one entity has been propelled with force so that it passes through another entity or barrier.
-
E.
throwsStyle
Indicates that one entity performs a throwing action using a particular style, technique, or manner.
- 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_69f348cae52081909fa8e5f697523ae3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a1e8f46c819085d3019e45989d9c |
completed | May 3, 2026, 1:16 a.m. |
| PD | Predicate disambiguation | batch_69f69fe82e5c81909da9db0a2f3bba6d |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 9:41 p.m.