Triple
T1035393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William B. Bankhead |
E22349
|
entity |
| Predicate | startTimeAsSpeakerOfTheHouse |
P1814
|
FINISHED |
| Object | 1936 |
—
|
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: 1936 | Statement: [William B. Bankhead, startTimeAsSpeakerOfTheHouse, 1936]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeAsSpeakerOfTheHouse Context triple: [William B. Bankhead, startTimeAsSpeakerOfTheHouse, 1936]
-
A.
startTimeAsUSCongressSeat
Indicates the date and time at which an individual officially begins serving in a specific seat in the U.S. Congress.
-
B.
termStartAsSpeaker
Indicates that an entity begins serving or acting in the role of a speaker at the start of a specified term or period.
-
C.
timeInOfficeBeginsIn
Indicates the point in time or date when an entity’s term, tenure, or period in office starts.
-
D.
officeHolderStartTime
chosen
Indicates the date and time at which an individual begins holding a particular office or position.
-
E.
succeededAsSpeakerBy
Indicates that one entity took over the role or position of speaker from another entity as their successor.
- 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_69a493d848848190aed4011b34b2e8d3 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b8d669448190955507e2e4975b9f |
completed | March 1, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69a4b728ad3481909cf1430349cb9bba |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.