Triple
T8939867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Public Law 73-67 |
E212871
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | NIRA |
E39110
|
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: NIRA | Statement: [Public Law 73-67, shortName, NIRA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NIRA Context triple: [Public Law 73-67, shortName, NIRA]
-
A.
NIRA
chosen
NIRA is the commonly used acronym for the National Industrial Recovery Act, a key 1933 New Deal law aimed at stabilizing the U.S. economy during the Great Depression.
-
B.
NIEA
NIEA is the government agency responsible for protecting, conserving, and promoting the natural and built environment in Northern Ireland.
-
C.
NSIRA
NSIRA is Canada’s independent federal body responsible for reviewing and overseeing the activities of the country’s national security and intelligence agencies.
-
D.
NIA
NIA is India’s premier federal counter-terrorism and national security investigation agency.
-
E.
NIA
NIA is a U.S. federal research institute within the National Institutes of Health that focuses on understanding aging and age-related diseases, including Alzheimer’s disease.
- 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_69ca839694c88190b324ffeb43d23b08 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66b7484481909e0d7610552f5386 |
completed | April 1, 2026, 12:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc1eb308c81909f5be133c75ad568 |
completed | April 3, 2026, 1:34 p.m. |
Created at: March 30, 2026, 6:58 p.m.