Triple
T25037633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Commanding General, III Corps |
E627021
|
entity |
| Predicate | timeInPosition |
P144212
|
FINISHED |
| Object | typically 2 to 3 years |
—
|
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: typically 2 to 3 years | Statement: [Commanding General, III Corps, timeInPosition, typically 2 to 3 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeInPosition Context triple: [Commanding General, III Corps, timeInPosition, typically 2 to 3 years]
-
A.
recordHeldDuration
chosen
Indicates the length of time for which a particular record, title, or achievement was continuously held.
-
B.
spentTimeIn
Indicates that an entity has spent a certain amount or period of time in a particular place or context.
-
C.
endTimePosition
Indicates the temporal position or point in time at which an event, state, or interval comes to an end.
-
D.
timeInCareer
Indicates the point or duration within an entity’s professional or occupational trajectory at which a related event, status, or condition occurs.
-
E.
positionStartTime
Indicates the time at which a position, role, or placement begins.
- 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_69e2ff2a2c088190be513727ee8bfe78 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f453078c988190b4d3afd630cfafa8 |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f442c861188190967655c6d8012380 |
completed | May 1, 2026, 6:06 a.m. |
Created at: April 18, 2026, 6:08 a.m.