Triple
T8305340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Contract with America |
E194449
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Dick Armey |
E37936
|
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: Dick Armey | Statement: [Contract with America, author, Dick Armey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dick Armey Context triple: [Contract with America, author, Dick Armey]
-
A.
Richard Armey
chosen
Richard Armey is an American economist and Republican politician who served as House Majority Leader and played a key role in advancing major conservative legislation in the U.S. Congress.
-
B.
Chip Roy
Chip Roy is a conservative Republican politician and attorney serving in the U.S. House of Representatives from Texas.
-
C.
Michael McCaul
Michael McCaul is a Republican U.S. Representative from Texas who has served in Congress since 2005 and is known for his work on national security and foreign affairs.
-
D.
Michael Steele
Michael Steele is an American political commentator and former chairman of the Republican National Committee.
-
E.
Tom DeLay
Tom DeLay is a former Republican House Majority Leader from Texas known for his influential role in Congress and subsequent legal and ethical controversies.
- 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_69ca82e613e88190bf8139669bbd0d53 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7e8db3a8819083772db5c7a2454b |
completed | March 31, 2026, 7:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc6dc4008819084eff0960917494c |
completed | April 2, 2026, 1:31 a.m. |
Created at: March 30, 2026, 5:54 p.m.