Triple
T28491496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcellus |
E720981
|
entity |
| Predicate | reportsAppearanceOf |
P21320
|
FINISHED |
| Object | Ghost of King Hamlet |
—
|
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: Ghost of King Hamlet | Statement: [Marcellus, reportsAppearanceOf, Ghost of King Hamlet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reportsAppearanceOf Context triple: [Marcellus, reportsAppearanceOf, Ghost of King Hamlet]
-
A.
reportsAs
Indicates that one entity formally reports information, status, or results to another entity.
-
B.
reportedFor
Indicates that one entity has formally notified an authority or system about another entity’s behavior, condition, or status, typically to trigger review or action.
-
C.
reportedAs
Indicates that one entity has been formally reported or flagged to another entity, typically as problematic, suspicious, or noteworthy.
-
D.
reportedOn
Indicates that one entity has provided an account, description, or coverage of another entity, typically as news, documentation, or an official report.
-
E.
reportedApparitionEntity
chosen
Indicates that an entity has been reported or described as an apparition in some account or observation.
- 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_69f01a5a47148190b0a7e111bc432e0a |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 3:01 a.m.