Triple
T16147597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stephen Petranek |
E391825
|
entity |
| Predicate | hasGivenPresentation |
P61190
|
FINISHED |
| Object | TED talk on 10 ways the world could end |
—
|
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: TED talk on 10 ways the world could end | Statement: [Stephen Petranek, hasGivenPresentation, TED talk on 10 ways the world could end]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGivenPresentation Context triple: [Stephen Petranek, hasGivenPresentation, TED talk on 10 ways the world could end]
-
A.
hasPresented
chosen
Indicates that one entity has formally given, delivered, or shown something (such as information, a work, or an award) to another entity.
-
B.
hasPresentation
Indicates that an entity delivers, contains, or is associated with a specific presentation (such as a talk, slide deck, or formal display of information).
-
C.
hasGiven
Indicates that one entity has transferred or presented something to another entity.
-
D.
presentedAfter
Indicates that one entity is presented or displayed at a later time or sequence position than another entity.
-
E.
hasArtFormPresented
Indicates that an entity presents, showcases, or features a particular art form.
- 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_69d87f1c65e48190aa2b4c472e9bafc4 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21d947e68819081b4b7c757ce71b6 |
completed | April 17, 2026, 11:46 a.m. |
| PD | Predicate disambiguation | batch_69e182885bc08190822ae7e8a4b8ac1f |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5:01 a.m.