Triple
T1445225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oil Pollution Act of 1990 |
E31161
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | OPA 90 |
E31161
|
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: OPA 90 | Statement: [Oil Pollution Act of 1990, shortName, OPA 90]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: OPA 90 Context triple: [Oil Pollution Act of 1990, shortName, OPA 90]
-
A.
OPA
chosen
OPA is a U.S. federal law enacted in 1990 that strengthens regulations and liability standards for preventing and responding to oil spills in navigable waters and shorelines.
-
B.
OPAL
OPAL was one of the major particle physics experiments at CERN’s Large Electron–Positron Collider, designed to study electron-positron collisions and probe the Standard Model.
-
C.
O.P.
O.P. is a common abbreviation that can stand for various phrases such as “original poster,” “original post,” or “out of print,” depending on the context in which it is used.
-
D.
OPO
OPO is the vehicle registration code assigned to the Polish city of Opole.
-
E.
POMA
POMA is a scholarly journal and conference proceedings series published by the Acoustical Society of America that disseminates research presented at acoustics meetings.
- 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_69a4991633388190a4d61b5a98aa407a |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c55714588190a95b4f677c21cbaa |
completed | March 1, 2026, 11:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad08c046b08190a448ba2549dc5e00 |
completed | March 8, 2026, 5:27 a.m. |
Created at: March 1, 2026, 8 p.m.