Triple
T20342275
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cameirus |
E495767
|
entity |
| Predicate | hasArchaeologicalExcavationsStart |
P28743
|
FINISHED |
| Object | 19th century |
—
|
LITERAL 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: 19th century | Statement: [Cameirus, hasArchaeologicalExcavationsStart, 19th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArchaeologicalExcavationsStart Context triple: [Cameirus, hasArchaeologicalExcavationsStart, 19th century]
-
A.
hasArchaeologicalExcavationsSince
chosen
Indicates that archaeological excavations have been conducted at an entity starting from a specified point in time and continuing since then.
-
B.
hasArchaeologicalExcavationsBy
Indicates that archaeological excavations at a site or location are or were conducted by a specified person, group, or organization.
-
C.
hasArchaeologicalResearch
Indicates that archaeological research has been conducted on, or is associated with, a given entity.
-
D.
hasArchaeologicalProject
Indicates that an entity is associated with or involved in a specific archaeological project.
-
E.
archaeologicallyExploredSince
Indicates that a place or site has been subject to archaeological exploration starting from a specified point in time.
- F. None of above.
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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67835f6e881908834dda06cf66c50 |
completed | April 20, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69e57636b4808190bc2855af48a3ccdc |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:24 a.m.