Triple
T16520582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anglona |
E401306
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Martis |
E423883
|
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: Martis | Statement: [Anglona, hasSettlement, Martis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martis Context triple: [Anglona, hasSettlement, Martis]
-
A.
Martis
chosen
Martis is a small town and comune in the Gallura region of northern Sardinia, Italy.
-
B.
Marti
Marti is a given name and surname used in various cultures, often as a variant of Martin.
-
C.
Maro
Maro is a small coastal village in the municipality of Nerja, in the province of Málaga, Spain, known for its nearby cliffs, beaches, and the famous Nerja Caves.
-
D.
Martz
Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
-
E.
Gardo
Gardo is one of the three impoverished boys who uncover a dangerous secret while scavenging through a landfill in Andy Mulligan’s novel "Trash."
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e7f8a1481909fe6b3c16a72059b |
completed | April 18, 2026, 7:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006088fe4881909e5b691743157700 |
completed | May 10, 2026, 10:40 a.m. |
Created at: April 10, 2026, 5:14 a.m.