Triple
T27970112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Joy of Data |
E706329
|
entity |
| Predicate | hasPresenterName |
P197291
|
FINISHED |
| Object | Hannah Fry |
—
|
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: Hannah Fry | Statement: [The Joy of Data, hasPresenterName, Hannah Fry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPresenterName Context triple: [The Joy of Data, hasPresenterName, Hannah Fry]
-
A.
hasPresenterType
Indicates the specific role or category of presenter associated with an event, item, or presentation.
-
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.
presenterField
Indicates that an entity serves as the presenter or speaker associated with a particular field, session, or content item.
-
D.
hasPresented
Indicates that one entity has formally given, delivered, or shown something (such as information, a work, or an award) to another entity.
-
E.
hasProperName
Indicates that an entity is associated with a specific proper name used to uniquely identify it.
- F. None of above. chosen
Provenance (4 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_69ef96b7f330819090f315318ba6977e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fe86cad5108190b0164b8bc6fc23ea |
completed | May 9, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69fe83c0c9888190b6fc40c7f727b569 |
completed | May 9, 2026, 12:45 a.m. |
| PDg | Predicate description generation | batch_69fe86c98d688190a99d5dcb14e2dc95 |
completed | May 9, 2026, 12:58 a.m. |
Created at: April 27, 2026, 7:37 p.m.