Triple
T7933437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google I/O |
E184234
|
entity |
| Predicate | primaryKeynoteBy |
P79855
|
FINISHED |
| Object | Google CEO |
—
|
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: Google CEO | Statement: [Google I/O, primaryKeynoteBy, Google CEO]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryKeynoteBy Context triple: [Google I/O, primaryKeynoteBy, Google CEO]
-
A.
notableKey
Indicates that the referenced key is of particular importance or prominence compared to other keys in the same context.
-
B.
key
Indicates that one entity functions as a key (literal or metaphorical) that unlocks, enables access to, or provides a crucial solution or control over another entity.
-
C.
keyTarget
Indicates that one entity serves as the primary focus, objective, or intended recipient of another entity’s action, function, or influence.
-
D.
keyOrganizer
Indicates a relationship where one entity is responsible for managing, arranging, or keeping track of keys for another entity or context.
-
E.
keyText
Indicates that a piece of text functions as a key or identifier used to access, reference, or unlock something in a system or context.
- 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_69ca8290c21c8190906a5ca6fe2b03c4 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3acfd2a88190b1a13cd6fdedc272 |
completed | March 31, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69cae9335f288190ba96781fd6576a2b |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf7882b048190baa333af9f698590 |
completed | March 30, 2026, 10:22 p.m. |
Created at: March 30, 2026, 5:08 p.m.