Triple
T407304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trooping the Colour |
E9409
|
entity |
| Predicate | hasPrecedingEvents |
P11018
|
FINISHED |
| Object | rehearsals on preceding Saturdays |
—
|
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: rehearsals on preceding Saturdays | Statement: [Trooping the Colour, hasPrecedingEvents, rehearsals on preceding Saturdays]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrecedingEvents Context triple: [Trooping the Colour, hasPrecedingEvents, rehearsals on preceding Saturdays]
-
A.
hasSubEvent
Indicates that an event is composed of, or includes as part of its structure, another event that occurs within it.
-
B.
hasHistoricalPrecursor
Indicates that one entity existed earlier and served as a predecessor, model, or influential forerunner to the other in a historical context.
-
C.
commemoratesEventBefore
Indicates that one entity performs an act of commemoration for an event that occurred prior in time to that act.
-
D.
cededTo
Indicates that control, ownership, or authority over something was formally transferred from one entity to another.
-
E.
precedentFor
Indicates that one situation, decision, or case serves as an authoritative example or basis for deciding or interpreting another.
- 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ecbd766c8190bb8a91605929156a |
completed | Feb. 28, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69a2e971a3a481909e6b075f25dd234a |
completed | Feb. 28, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69a2ea4545608190898436c72e10f39d |
completed | Feb. 28, 2026, 1:14 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.