Triple
T38591387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Onslaught |
E932460
|
entity |
| Predicate | isContentUpdateFor |
P100199
|
FINISHED |
| Object | live service game |
—
|
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: live service game | Statement: [Onslaught, isContentUpdateFor, live service game]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isContentUpdateFor Context triple: [Onslaught, isContentUpdateFor, live service game]
-
A.
isUpdateFor
chosen
Indicates that one entity serves as a newer or modified version that replaces or revises another entity.
-
B.
contentUpdateType
Indicates the specific kind of modification or change that has been applied to a piece of content (e.g., creation, edit, or deletion).
-
C.
isUpdateType
Indicates that one entity represents the type or category of an update operation associated with another entity.
-
D.
isUpdated
Indicates that an entity has been modified or brought to a more recent state compared to its previous version or a reference point.
-
E.
isUpdatedWhen
Indicates that one entity undergoes a change or refresh whenever another specified entity is modified or updated.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 3, 2026, 4:32 p.m.