Triple
T2923852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olympique Lyonnais |
E78796
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | OL |
E304419
|
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: OL | Statement: [Olympique Lyonnais, shortName, OL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: OL Context triple: [Olympique Lyonnais, shortName, OL]
-
A.
OL
OL is a UK postcode area covering Oldham and surrounding parts of Greater Manchester and nearby regions in North West England.
-
B.
OL
chosen
OL is the commonly used abbreviation for Olympique Lyonnais, a major French football club best known internationally for its highly successful women's team.
-
C.
OLE
OLE (Object Linking and Embedding) is a Microsoft technology that enables embedding and linking to documents and other objects within different applications, forming a foundation for later component technologies like ActiveX.
-
D.
OLA
OLA is the commonly used acronym for the United Nations Office of Legal Affairs, which provides legal advice and support to UN organs and specialized agencies.
-
E.
OH
OH is the official United States Postal Service abbreviation for the state of Ohio.
- 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_69ad8b0d40b481908bc2a5fa2e73c3fb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad97bf2df88190bd4f1e90d4656507 |
completed | March 8, 2026, 3:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b08664fe308190889e855821a32576 |
completed | March 10, 2026, 9 p.m. |
Created at: March 8, 2026, 2:55 p.m.