Triple
T23396221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earls of Mar |
E559366
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Mar |
—
|
NE NERFINISHED |
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: Mar | Statement: [Earls of Mar, region, Mar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mar Context triple: [Earls of Mar, region, Mar]
-
A.
Mar
Mar is an honorific ecclesiastical title used for bishops and saints in several Eastern Christian traditions, particularly within Syriac Christianity.
-
B.
Mar
chosen
Mar is a historic earldom and region in Aberdeenshire, Scotland, long associated with one of the oldest Scottish peerage titles, the Earldom of Mar.
-
C.
MA
MA is the IATA airline designator formerly assigned to Malév Hungarian Airlines, the former flag carrier of Hungary.
-
D.
MA
MA is the vehicle registration code used on license plates for the German city of Mannheim.
-
E.
MA
MA is the commonly used abbreviation for the Supreme Court of Indonesia, the country's highest judicial authority.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24549610c8190a069d6411ce5f661 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a4dc48008190bdcf92f8d9a5232d |
completed | April 29, 2026, 6:27 a.m. |
Created at: April 17, 2026, 5:36 p.m.