Triple
T8837107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alor archipelago |
E210291
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Kalabahi |
E661217
|
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: Kalabahi | Statement: [Alor archipelago, hasCity, Kalabahi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kalabahi Context triple: [Alor archipelago, hasCity, Kalabahi]
-
A.
Kalabahi
chosen
Kalabahi is the main town and administrative center on Alor Island in Indonesia’s East Nusa Tenggara province.
-
B.
Qanjobal
Qanjobal is a Mayan language spoken primarily by the Qʼanjobʼal people in the highlands of Guatemala.
-
C.
Kaxabu
Kaxabu is an indigenous Formosan language of Taiwan traditionally spoken by the Kaxabu people.
-
D.
Jableh
Jableh is a coastal city in northwestern Syria on the Mediterranean Sea, known for its ancient history and archaeological sites, including a well-preserved Roman theater.
-
E.
Kabaena
Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly 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_69ca8388549c819095fd94eadefbb007 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc606adde08190825dbdabd199c025 |
completed | April 1, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf898a478c81908f138a78f331b87d |
completed | April 3, 2026, 9:34 a.m. |
Created at: March 30, 2026, 6:48 p.m.