Triple
T12543971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Directi Group |
E299912
|
entity |
| Predicate | subsidiary |
P258
|
FINISHED |
| Object | Zeta |
E989511
|
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: Zeta | Statement: [Directi Group, subsidiary, Zeta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zeta Context triple: [Directi Group, subsidiary, Zeta]
-
A.
Zeta
Zeta is a historical region in present-day Montenegro that once formed a medieval principality and early state precursor to the country.
-
B.
Zeta
chosen
Zeta is a fintech company known for providing digital payments, banking, and card management solutions, and operates as part of the Directi Group.
-
C.
Zeta
Zeta is the sixth letter of the Greek alphabet, corresponding roughly to the English "z" sound.
-
D.
Upsilon
Upsilon is a letter of the Greek alphabet that historically represented a "u" or "y" vowel sound and is used in various scientific and mathematical contexts.
-
E.
Epsilon
Epsilon is the fifth letter of the Greek alphabet, commonly used in mathematics and science to denote small quantities or error terms.
- 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_69d6ada707008190aaec1238117c9379 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d9547d6df4819080db8415d386ed38 |
completed | April 10, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65eb317148190990d47f50324a1b1 |
completed | May 2, 2026, 8:29 p.m. |
Created at: April 8, 2026, 9:57 p.m.