Triple
T25765202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Metcalfe |
E648862
|
entity |
| Predicate | yearOfStartPosition |
P10338
|
FINISHED |
| Object | 1828 as Governor of Kentucky |
—
|
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: 1828 as Governor of Kentucky | Statement: [Thomas Metcalfe, yearOfStartPosition, 1828 as Governor of Kentucky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearOfStartPosition Context triple: [Thomas Metcalfe, yearOfStartPosition, 1828 as Governor of Kentucky]
-
A.
beganInYear
chosen
Indicates that an event, process, or state started in a specific calendar year.
-
B.
startsYearOn
Indicates that a specified time period or calendar year begins on a particular date or day.
-
C.
recordStartYear
Indicates the calendar year in which a particular record, entry, or data instance first began or was created.
-
D.
typicalStartYear
Indicates the year in which something (such as an event, activity, or process) usually or customarily begins.
-
E.
coachStartYear
Indicates the year in which a person began serving in a coaching role for a particular team or organization.
- 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_69e7ab322db0819092d6a2b3d4572e01 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f68805b4848190b75da14996d52a38 |
completed | May 2, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f68609c0b08190a8e1238a4d97c270 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 22, 2026, 5:09 a.m.