Triple
T33888990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Fort Pulaski |
E868705
|
entity |
| Predicate | breach |
P177877
|
FINISHED |
| Object | southeast wall of Fort Pulaski |
—
|
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: southeast wall of Fort Pulaski | Statement: [Siege of Fort Pulaski, breach, southeast wall of Fort Pulaski]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: breach Context triple: [Siege of Fort Pulaski, breach, southeast wall of Fort Pulaski]
-
A.
breachedDuring
Indicates that one entity violated, broke, or failed to uphold another entity (such as a rule, contract, or security measure) within a specified time period or event.
-
B.
break
Indicates that one entity causes another entity to separate into pieces, stop functioning, or otherwise lose its normal integrity or continuity.
-
C.
breachedAt
Indicates the specific time or point at which a security, contract, or boundary was violated or broken.
-
D.
afterBreached
Indicates that one event or state occurs subsequent to another event or state having been breached or violated.
-
E.
broke
Indicates that one entity caused another entity to separate into pieces or cease functioning, typically through force or damage.
- 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_69f34996761c8190864e42f7c9cf215b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7051ad6e4819095e82bbd64761803 |
completed | May 3, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69f700fe24e08190998e2c96fbaaad38 |
completed | May 3, 2026, 8:02 a.m. |
| PDg | Predicate description generation | batch_69f70519f114819080659840c04d7911 |
completed | May 3, 2026, 8:19 a.m. |
Created at: May 1, 2026, 1:48 a.m.