Triple
T25544419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of Don Andrea |
E640257
|
entity |
| Predicate | isRecountedBy |
P59712
|
FINISHED |
| Object | ghost of Don Andrea |
—
|
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: ghost of Don Andrea | Statement: [murder of Don Andrea, isRecountedBy, ghost of Don Andrea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isRecountedBy Context triple: [murder of Don Andrea, isRecountedBy, ghost of Don Andrea]
-
A.
isCountedAs
Indicates that one entity is treated or included as part of the tally, total, or quantitative assessment of another entity.
-
B.
areCountedBy
Indicates that one entity serves as the counting mechanism, record, or process by which the quantity of another entity is determined.
-
C.
ballotsCountedBy
Indicates that the ballots in an election or vote are counted or tallied by a specified person, group, or entity.
-
D.
recount
chosen
Indicates that an entity narrates or describes past events or experiences, often in a detailed or sequential manner, to another entity.
-
E.
voteCountedIn
Indicates that a particular vote has been included in the official tally for a specific election, contest, or jurisdiction.
- 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_69e75dbfff7081909b0aa779d48321d2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f896f04c81908294db99385b464e |
completed | May 2, 2026, 1:13 p.m. |
| PD | Predicate disambiguation | batch_69f480789be08190ab252a6de3797200 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 3:28 p.m.