Triple
T32327554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caroline Alice Elgar |
E825953
|
entity |
| Predicate | sharesGraveWith |
P199639
|
FINISHED |
| Object | Edward Elgar |
—
|
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: Edward Elgar | Statement: [Caroline Alice Elgar, sharesGraveWith, Edward Elgar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesGraveWith Context triple: [Caroline Alice Elgar, sharesGraveWith, Edward Elgar]
-
A.
sharesSlainWith
Indicates that two or more entities have killed the same target or share responsibility for the same slaying event.
-
B.
sharesImmortalityWith
Indicates that one entity grants or mutually possesses an immortal or deathless state together with another entity.
-
C.
sharesFateWith
Indicates that two or more entities are bound to experience the same outcome, destiny, or consequences.
-
D.
hasPartInGrave
Indicates that an entity includes another entity as a physical component or element within a grave.
-
E.
associatedCemetery
Indicates that there is a relationship linking an entity (such as a person, event, or organization) to a specific cemetery with which it is connected.
- 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_69f34912d0c48190bba75770660320e9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff49f888348190b9c55afa73b99e6a |
completed | May 9, 2026, 2:51 p.m. |
| PD | Predicate disambiguation | batch_69ff49614ef88190ac70b034c55ad738 |
completed | May 9, 2026, 2:49 p.m. |
| PDg | Predicate description generation | batch_69ff49f7db2c819094d488d13985334c |
completed | May 9, 2026, 2:51 p.m. |
Created at: May 1, 2026, 12:47 a.m.