Triple
T4961617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Murphy |
E111420
|
entity |
| Predicate | startTime (as Mayor of Detroit) |
P17454
|
FINISHED |
| Object | 1930-01-06 |
—
|
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: 1930-01-06 | Statement: [Frank Murphy, startTime (as Mayor of Detroit), 1930-01-06]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTime (as Mayor of Detroit) Context triple: [Frank Murphy, startTime (as Mayor of Detroit), 1930-01-06]
-
A.
officeStartForMayorOfNewYorkCity
Indicates the date on which an individual begins their term in office as the Mayor of New York City.
-
B.
mayoralTermStart
chosen
Indicates the date or point in time when an individual's tenure as mayor officially begins.
-
C.
startTime (CIA directorship)
Indicates the calendar date and/or time at which a specific tenure as CIA Director officially began.
-
D.
wonMayoraltyOf
Indicates that one entity won the election to become mayor of a specified place or jurisdiction.
-
E.
startTime (Senate Majority Leader)
Indicates the specific time at which the person serves or begins serving as Senate Majority Leader.
- 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_69bd4419393c819086319a6fe4bf8542 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd72e49b048190bac55d9e7a6f7963 |
completed | March 20, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_69bd71447fe88190bb62c5e8753da7a7 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:32 p.m.