Triple
T19206579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghost |
E480248
|
entity |
| Predicate | crewTreatmentOnboard |
P134967
|
FINISHED |
| Object | brutal |
—
|
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: brutal | Statement: [Ghost, crewTreatmentOnboard, brutal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crewTreatmentOnboard Context triple: [Ghost, crewTreatmentOnboard, brutal]
-
A.
crewOnboard
Indicates that a person or group is serving as crew aboard a specific vehicle, vessel, or craft.
-
B.
crewTended
Indicates that a crew is responsible for attending to, operating, or maintaining something or someone.
-
C.
crew
Indicates that one entity serves as the group of people who operate, staff, or work on another entity (such as a vehicle, vessel, or production).
-
D.
crewMate
Indicates that two entities are members of the same crew or team, sharing a common group affiliation or working together in a joint capacity.
-
E.
crewInvolvedIn
Indicates that a crew (as a group or unit) participates in, contributes to, or is otherwise involved in a specified event, activity, or operation.
- 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5f99d8ad0819098ebd4ee007149f1 |
completed | April 20, 2026, 10:02 a.m. |
| PD | Predicate disambiguation | batch_69e4dcf22b3c8190bee02e3af946e114 |
completed | April 19, 2026, 1:47 p.m. |
| PDg | Predicate description generation | batch_69e4ddcf50108190a09d0f1291c17374 |
completed | April 19, 2026, 1:51 p.m. |
Created at: April 10, 2026, 1:19 p.m.