Triple
T10832988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ian McKay |
E255670
|
entity |
| Predicate | militaryUnit |
P1063
|
FINISHED |
| Object | 3 PARA |
E319438
|
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: 3 PARA | Statement: [Ian McKay, militaryUnit, 3 PARA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 3 PARA Context triple: [Ian McKay, militaryUnit, 3 PARA]
-
A.
3 PARA
chosen
3 PARA is a battalion of the British Army’s Parachute Regiment renowned for its airborne infantry role and distinguished combat service, including in the Falklands War.
-
B.
4 PARA
4 PARA is a British Army Reserve airborne infantry battalion of the Parachute Regiment known for its elite paratrooper training and rapid deployment role.
-
C.
1 PARA
1 PARA is an elite British Army airborne infantry battalion renowned for its rapid deployment capabilities and role within the Parachute Regiment.
-
D.
P3
P3 is a major Swedish national radio channel from public broadcaster Sveriges Radio, primarily focused on contemporary popular music and youth-oriented programming.
-
E.
PAR
PAR is the IATA city code representing the collective airport system serving Paris, France, including major airports such as Charles de Gaulle and Orly.
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7442439dc8190af59f9c8d0637c01 |
completed | April 9, 2026, 6:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de85aa5ea88190ab6399e46eba5c49 |
completed | April 14, 2026, 6:21 p.m. |
Created at: April 8, 2026, 9:19 p.m.