Triple
T28629072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco City Hall |
E724594
|
entity |
| Predicate | destroyedPredecessor |
P130508
|
FINISHED |
| Object | 1906 San Francisco 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: 1906 San Francisco earthquake | Statement: [San Francisco City Hall, destroyedPredecessor, 1906 San Francisco earthquake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: destroyedPredecessor Context triple: [San Francisco City Hall, destroyedPredecessor, 1906 San Francisco earthquake]
-
A.
predecessorDestroyed
Indicates that one entity has caused the destruction or elimination of another entity that existed or acted before it.
-
B.
removedElementFromPredecessor
Indicates that an element has been taken out or deleted from an immediately preceding entity in a sequence or structure.
-
C.
calledPredecessorOf
Indicates that one entity is referred to or designated as the predecessor of another entity.
-
D.
possiblyDestroyedIn
chosen
Indicates that an entity may have been destroyed during or as a result of a specified event or situation.
-
E.
ownedByPredecessor
Indicates that something is or was owned by an entity that previously held a given role, position, or status before the current one.
- 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_69f01d822ac08190932de59ec2268ed2 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:37 a.m.