Triple
T3405016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quintana Roo |
E71749
|
entity |
| Predicate | hasArchaeologicalSite |
P1098
|
FINISHED |
| Object | Kohunlich |
E238694
|
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: Kohunlich | Statement: [Quintana Roo, hasArchaeologicalSite, Kohunlich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kohunlich Context triple: [Quintana Roo, hasArchaeologicalSite, Kohunlich]
-
A.
Kohunlich
chosen
Kohunlich is a large Maya archaeological site in southern Quintana Roo, Mexico, noted for its monumental architecture and well-preserved stucco masks.
-
B.
Yakhin
Yakhin is a variant form of the biblical name Jachin, traditionally associated with one of the two pillars of Solomon’s Temple.
-
C.
Krakhuna
Krakhuna is a Georgian white grape variety from the Imereti region, known for producing aromatic, full-bodied wines with pronounced acidity.
-
D.
Kykuit
Kykuit is a historic Rockefeller family estate and grand mansion known for its architecture, art collections, and landscaped gardens overlooking the Hudson River in New York.
-
E.
Khoni
Khoni is a small town in western Georgia’s Imereti region, known for its historical churches and surrounding natural landscapes.
- 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_69ad85aac4808190a092c9cc8911f584 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb8eaa41c819095a4d51aec074649 |
completed | March 8, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b35468916c8190ba6caa2c53e01d9c |
completed | March 13, 2026, 12:03 a.m. |
Created at: March 8, 2026, 3:15 p.m.