Triple
T25544434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | murder of Don Andrea |
E640257
|
entity |
| Predicate | isExplainedThrough |
P142360
|
FINISHED |
| Object | ghost’s prologue |
—
|
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’s prologue | Statement: [murder of Don Andrea, isExplainedThrough, ghost’s prologue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isExplainedThrough Context triple: [murder of Don Andrea, isExplainedThrough, ghost’s prologue]
-
A.
usedToExplain
Indicates that one entity serves as an explanation or clarification for another entity.
-
B.
laterExplained
Indicates that an earlier event, statement, or situation is clarified or made understandable by information provided at a subsequent time.
-
C.
documentedThrough
Indicates that something is recorded, evidenced, or made known by means of a specific document or documentation process.
-
D.
providesExpositionAbout
chosen
Indicates that one entity offers explanatory or background information clarifying or elaborating on another entity.
-
E.
isRevealedIn
Indicates that something becomes known, disclosed, or made apparent within a particular context, medium, or situation.
- 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_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 3:28 p.m.