Triple
T6030901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunken Road |
E134298
|
entity |
| Predicate | timeOfMainAction |
P57350
|
FINISHED |
| Object | late morning to early afternoon on September 17, 1862 |
—
|
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: late morning to early afternoon on September 17, 1862 | Statement: [Sunken Road, timeOfMainAction, late morning to early afternoon on September 17, 1862]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfMainAction Context triple: [Sunken Road, timeOfMainAction, late morning to early afternoon on September 17, 1862]
-
A.
timeOfMainAssault
Indicates the specific time at which the primary or main assault event occurred.
-
B.
hasTimeOfAction
chosen
Indicates that an action is associated with a specific point or interval in time when it occurs.
-
C.
timeAfterAble
Indicates that one event, state, or action occurs after another point in time at which it becomes possible or permissible.
-
D.
timeOfInitiation
Indicates the specific point in time at which an action, event, or process begins.
-
E.
timeOfSetting
Indicates the specific time at which an event, object, or phenomenon is set, scheduled, or takes place.
- 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_69c0087515148190a97475d412563865 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c056af89e881909652957f94317684 |
completed | March 22, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69c049e9a68c81909da0cfe4779ce9b5 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:08 p.m.