Triple
T6899032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Ferguson |
E159445
|
entity |
| Predicate | startTimeOfHosting |
P35512
|
FINISHED |
| Object | The Late Late Show with Craig Ferguson, 2005 |
—
|
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: The Late Late Show with Craig Ferguson, 2005 | Statement: [Craig Ferguson, startTimeOfHosting, The Late Late Show with Craig Ferguson, 2005]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeOfHosting Context triple: [Craig Ferguson, startTimeOfHosting, The Late Late Show with Craig Ferguson, 2005]
-
A.
hostedDuring
chosen
Indicates that one entity hosted, organized, or held another entity (such as an event or activity) within a specified time period.
-
B.
startsAt
Indicates that an event, process, or state begins at a specific time, location, or point in a sequence.
-
C.
startTimeAsRepresentative
Indicates the time at which an entity begins serving or acting in a representative capacity.
-
D.
timeOfInitiation
Indicates the specific point in time at which an action, event, or process begins.
-
E.
plannedToHost
Indicates that an entity had the intention or arrangement to host an event, activity, or gathering.
- 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_69c6883822e0819091e321526f20ae0a |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d95d67448190857f36b8115b03f6 |
completed | March 27, 2026, 7:24 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b7681481909ec50509b19fcf81 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:24 p.m.