Triple
T2196438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlanta Campaign |
E49984
|
entity |
| Predicate | dateCaptureOfAtlanta |
P10180
|
FINISHED |
| Object | 1864-09-02 |
—
|
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: 1864-09-02 | Statement: [Atlanta Campaign, dateCaptureOfAtlanta, 1864-09-02]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateCaptureOfAtlanta Context triple: [Atlanta Campaign, dateCaptureOfAtlanta, 1864-09-02]
-
A.
capturedAt
Indicates the specific time or moment at which an entity was captured, recorded, or taken.
-
B.
dateOfCityCapture
chosen
Indicates the specific date on which a city was taken or captured, typically in a military or political context.
-
C.
capturedDuring
Indicates that one event or state occurred within the temporal span of another, typically representing that something was recorded, seized, or documented while a specific situation or activity was taking place.
-
D.
dateOfArrest
Indicates the specific date on which an entity was formally arrested by an authority.
-
E.
arrestedAt
Indicates that an entity was apprehended or taken into custody at a specific location or during a specific event or time.
- 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_69a88aaba3c48190b351cab9b26989ff |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbf77e4f08190a1f5ea601d306596 |
completed | March 7, 2026, 6:02 a.m. |
| PD | Predicate disambiguation | batch_69abbda52328819089c7ab111bebb0ca |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:46 p.m.