Triple
T30796197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canterbury Earthquake Recovery Authority |
E784234
|
entity |
| Predicate | createdFollowingEvent |
P3117
|
FINISHED |
| Object | 2010 Canterbury earthquake |
—
|
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: 2010 Canterbury earthquake | Statement: [Canterbury Earthquake Recovery Authority, createdFollowingEvent, 2010 Canterbury earthquake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdFollowingEvent Context triple: [Canterbury Earthquake Recovery Authority, createdFollowingEvent, 2010 Canterbury earthquake]
-
A.
createdAfterEvent
chosen
Indicates that the creation of one entity occurred after a specified event in time.
-
B.
followerEvent
Indicates that one entity begins or performs the action of following another entity, typically recorded as a discrete event in time.
-
C.
eventFollowedBy
Indicates that one event occurs after and in sequence with another event.
-
D.
adoptedFollowing
Indicates that one entity formally took on or implemented another entity after or as a result of the occurrence of a preceding event, state, or action.
-
E.
endedFollowing
Indicates that one entity stopped following or subscribing to another entity after previously doing so.
- 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_69f224b2e2a48190b19aa43db9da5b67 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
Created at: April 29, 2026, 8:42 p.m.