Triple
T24087425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greed |
E596685
|
entity |
| Predicate | editingHistory |
P88939
|
FINISHED |
| Object | heavily cut by studio from original length |
—
|
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: heavily cut by studio from original length | Statement: [Greed, editingHistory, heavily cut by studio from original length]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editingHistory Context triple: [Greed, editingHistory, heavily cut by studio from original length]
-
A.
editHistoryPublic
Indicates that the record of changes or revisions made to an item is visible to others.
-
B.
historicalModification
chosen
Indicates that one entity has altered, updated, or otherwise changed another entity at some point in the past, with the modification recorded as part of its history.
-
C.
editingIs
Indicates that one entity is performing or undergoing the process of editing another entity.
-
D.
formatHistory
Indicates that one entity records or structures the sequence of past states, events, or changes associated with another entity into a specific format.
-
E.
editedTo
Indicates that one entity has been modified, revised, or altered in order to become the other entity.
- 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_69e288c4638c81909bacc28a1e3d436b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dc2b555481909ffcd2898fdd51fa |
completed | April 29, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 10:45 p.m.