Triple
T14999007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uhuru Torch |
E374032
|
entity |
| Predicate | eventCustom |
P1664
|
FINISHED |
| Object | annual Uhuru Torch relay |
—
|
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: annual Uhuru Torch relay | Statement: [Uhuru Torch, eventCustom, annual Uhuru Torch relay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eventCustom Context triple: [Uhuru Torch, eventCustom, annual Uhuru Torch relay]
-
A.
eventManagement
Indicates the organization, coordination, and oversight of all activities and resources involved in planning and executing an event.
-
B.
eventScale
Indicates the relative magnitude or size at which an event occurs or is characterized.
-
C.
eventUse
Indicates that an event involves the use or utilization of a particular entity (e.g., a resource, tool, or method) as part of its occurrence.
-
D.
event
chosen
Indicates that there exists an occurrence or happening involving one or more entities, typically situated in time and possibly space.
-
E.
eventIn
Indicates that an event occurs within, or is situated in, a specific location, context, or larger event.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded71a5618819083ae96a79735ef98 |
completed | April 15, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69de9a6169b48190a679609febd2d0e3 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:54 a.m.