Triple
T82983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madam President |
E1667
|
entity |
| Predicate | contrastWith |
P278
|
FINISHED |
| Object | Madam Speaker |
E4551
|
NE 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: Madam Speaker | Statement: [Madam President, contrastWith, Madam Speaker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madam Speaker Context triple: [Madam President, contrastWith, Madam Speaker]
-
A.
Madam Speaker
chosen
"Madam Speaker" is the formal mode of address used for a woman serving as Speaker of the United States House of Representatives.
-
B.
Madam President
"Madam President" is the formal style of address used for a female President of the United States.
-
C.
Mister Speaker
Mister Speaker is the traditional formal address used for a male Speaker presiding over the United States House of Representatives.
-
D.
Mr. President
"Mr. President" is the formal spoken address traditionally used for the sitting President of the United States.
-
E.
Madam Secretary
"Madam Secretary" is the formal style of address used when speaking to or about a female United States Secretary of the Army.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a24c8150408190910a693eb51c1f71 |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a2567c90308190a9b989c586f7e559 |
completed | Feb. 28, 2026, 2:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a29178a7348190a8cb9096ddc7c53e |
completed | Feb. 28, 2026, 6:55 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.