Triple
T21557366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Moab |
E531928
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Dibon |
—
|
NE NERFINISHED |
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: Dibon | Statement: [Kingdom of Moab, capital, Dibon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dibon Context triple: [Kingdom of Moab, capital, Dibon]
-
A.
Dibon
chosen
Dibon was an ancient Moabite city east of the Dead Sea, known from biblical texts and archaeological remains including the famous Mesha Stele.
-
B.
Darbenai
Darbenai is a small town in western Lithuania, historically home to a Jewish community from which Zionist leader David Wolffsohn originated.
-
C.
Dunagan
Dunagan is a surname of likely Irish or Scottish origin borne by various individuals, including American actress Deanna Dunagan.
-
D.
Dinsor
Dinsor is a town in southwestern Somalia located inland in the Bay region.
-
E.
Deran
Deran is a masculine given name used in various cultures, sometimes as a variant of names like Darren or Doran.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c460232c81908de2c3819d17c00e |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eed2e04b048190ac3a9913094b4625 |
completed | April 27, 2026, 3:07 a.m. |
Created at: April 16, 2026, 6:29 p.m.