Triple
T2472708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Internet Archive |
E55012
|
entity |
| Predicate | supportsSearch |
P21822
|
FINISHED |
| Object | full-text search of many collections |
—
|
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: full-text search of many collections | Statement: [Internet Archive, supportsSearch, full-text search of many collections]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsSearch Context triple: [Internet Archive, supportsSearch, full-text search of many collections]
-
A.
searchFeature
chosen
Indicates that an entity provides or supports functionality for searching or querying information or items.
-
B.
supportsUse
Indicates that one entity enables, allows, or is compatible with the use or operation of another entity.
-
C.
usedToSearchFor
Indicates that one entity serves as a tool, method, or resource employed to look for, locate, or retrieve another entity.
-
D.
searchesVia
Indicates that an entity performs a search by means of, or using, a specified tool, method, or channel.
-
E.
supportedAs
Indicates that one entity is accepted, recognized, or treated as being in the role, type, or representation of another 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_69ab49e279e88190ab10d7248aea9d11 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd1eb3be481908fa7c6b8f1c78209 |
completed | March 7, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69abd0b5e3d481909a5cbc4a96edd24f |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:45 p.m.