Triple
T1476086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emma |
E30843
|
entity |
| Predicate | usedInLanguage |
P907
|
FINISHED |
| Object | Maltese |
E51443
|
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: Maltese | Statement: [Emma, usedInLanguage, Maltese]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maltese Context triple: [Emma, usedInLanguage, Maltese]
-
A.
Maltese
chosen
Maltese is a Semitic language with significant Romance and English influences, spoken primarily in Malta and written in the Latin alphabet.
-
B.
Dhivehi language
Dhivehi is an Indo-Aryan language primarily spoken in the Maldives and on India’s Minicoy Island, serving as the national language of the Maldivian people.
-
C.
Manx
Manx is a Celtic language of the Goidelic branch traditionally spoken on the Isle of Man.
-
D.
Llanito
Llanito is a unique vernacular spoken in Gibraltar that blends Andalusian Spanish, British English, and elements from other Mediterranean languages.
-
E.
Sardinian language
The Sardinian language is a Romance language spoken on the island of Sardinia, noted for preserving many archaic features of Latin more than any other modern Romance tongue.
- 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_69a498fe55a88190ab7f9e40ace88e49 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c602387c8190b97a20c8e05e3d16 |
completed | March 1, 2026, 11:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad15ab9430819094deb90436983036 |
completed | March 8, 2026, 6:22 a.m. |
Created at: March 1, 2026, 8:11 p.m.