Triple
T3873811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USAP Perpignan |
E92448
|
entity |
| Predicate | league |
P888
|
FINISHED |
| Object | Pro D2 |
E331930
|
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: Pro D2 | Statement: [USAP Perpignan, league, Pro D2]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pro D2 Context triple: [USAP Perpignan, league, Pro D2]
-
A.
Pro D2
chosen
Pro D2 is the second-highest level of professional rugby union league in France, sitting just below the Top 14.
-
B.
D-2
D-2 was a 1993 German-led Spacelab space shuttle mission focused on microgravity and life sciences research in low Earth orbit.
-
C.
D2
D2 is a line of the Moscow Central Diameters suburban rail system, providing cross-city commuter rail service through Moscow and its surrounding areas.
-
D.
D6
D6 is the commonly used abbreviation for District 6, a designated administrative or electoral subdivision within a larger governmental or organizational structure.
-
E.
ProA
ProA is the second-highest professional basketball league in Germany, sitting just below the Basketball Bundesliga in the national league system.
- 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_69aed967448c819086c4b358d37b25aa |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec581adc81909219e6f025fc97c2 |
completed | March 9, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5124cdf588190b3b83ee8fb29450a |
completed | March 14, 2026, 7:46 a.m. |
Created at: March 9, 2026, 3:20 p.m.