Triple
T37783371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Enderlings |
E941886
|
entity |
| Predicate | contentPack |
P98691
|
FINISHED |
| Object | Echoing Void |
—
|
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: Echoing Void | Statement: [Enderlings, contentPack, Echoing Void]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contentPack Context triple: [Enderlings, contentPack, Echoing Void]
-
A.
contentBundleNumber
Indicates the identifying number assigned to a specific content bundle within a collection or system.
-
B.
expansionPack
chosen
Indicates that one item serves as an add-on or supplementary content package that extends the features or scope of another item.
-
C.
packaging
Indicates that one entity serves as the container, wrapper, or enclosing material used to package another entity.
-
D.
visualPackage
Indicates that one entity is a visual bundle or collection that groups together related visual elements or components associated with another entity.
-
E.
distributionPackage
Indicates that one entity is a package or bundle used to distribute another entity (such as software, content, or resources).
- 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_69f76ee5cb0c81909a363d1c929156c0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fd231cab588190ad0953dc8f4af8f2 |
completed | May 7, 2026, 11:41 p.m. |
| PD | Predicate disambiguation | batch_69fd1aa3f1c481909fe6e9cab1383551 |
completed | May 7, 2026, 11:05 p.m. |
Created at: May 3, 2026, 4:19 p.m.