Triple
T17076121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3i Group |
E414351
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | 3i |
E644853
|
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: 3i | Statement: [3i Group, abbreviation, 3i]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 3i Context triple: [3i Group, abbreviation, 3i]
-
A.
3i
chosen
3i is a leading international private equity and venture capital firm based in the United Kingdom, known for investing in and acquiring growth-oriented businesses across various sectors.
-
B.
I3
I3 is the IATA airline designator formerly assigned to ATA Airlines, a now-defunct U.S. low-cost carrier.
-
C.
S-I
S-I was the first-stage booster of NASA’s early Saturn I launch vehicle, providing the initial thrust for some of the United States’ first heavy-lift test flights in the Apollo era.
-
D.
I3A
I3A is a global trade association representing companies and organizations involved in the imaging and photographic technology industry.
-
E.
Si
Si is one of the mischievous Siamese cats from Disney’s animated film "Lady and the Tramp," known for causing trouble with her twin, Am.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc559388190b685504cca6ed62b |
completed | April 18, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012edfda588190aff6c6d4c8d64ddd |
completed | May 11, 2026, 1:20 a.m. |
Created at: April 10, 2026, 5:34 a.m.