Triple
T15009073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tmutarakan |
E377786
|
entity |
| Predicate | archaeologicalSiteAt |
P18735
|
FINISHED |
| Object | Taman |
E1091789
|
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: Taman | Statement: [Tmutarakan, archaeologicalSiteAt, Taman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taman Context triple: [Tmutarakan, archaeologicalSiteAt, Taman]
-
A.
Taman
chosen
Taman is a rural settlement on Russia’s Taman Peninsula, near the Black Sea and the Kerch Strait, known for its historical ties to ancient Greek colonies and strategic coastal location.
-
B.
Taman
Taman is a Nilo-Saharan language spoken by the Taman people in parts of Chad and Sudan.
-
C.
Taman Kosas
Taman Kosas is a residential township located within the municipality of Ampang Jaya in Selangor, Malaysia.
-
D.
Taman Ujung
Taman Ujung is a historic water palace and scenic royal garden complex in eastern Bali, Indonesia, known for its ornate pools, pavilions, and ocean views.
-
E.
Taman Dagang
Taman Dagang is a residential neighborhood located within the municipality of Ampang Jaya in Selangor, Malaysia.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded734943481908dad4ceed4fe850c |
completed | April 15, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9dce8240819097efddb43b79ad4b |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 2:55 a.m.