Triple
T21557611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koura |
E531933
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object | Enfeh |
—
|
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: Enfeh | Statement: [Koura, hasTown, Enfeh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Enfeh Context triple: [Koura, hasTown, Enfeh]
-
A.
Enfeh
chosen
Enfeh is a historic coastal town in northern Lebanon known for its ancient ruins, salt pans, and distinctive rocky peninsula on the Mediterranean Sea.
-
B.
Khalfun
Khalfun was an early medieval Muslim leader who ruled the Emirate of Bari in southern Italy during its period as an Islamic stronghold in the 9th century.
-
C.
Tahmoh
Tahmoh is a masculine given name most notably borne by Canadian actor Tahmoh Penikett.
-
D.
Dansili
Dansili was a top-class British Thoroughbred racehorse who became an elite international sire, known for producing numerous Group 1 winners on turf.
-
E.
Puduhepa
Puduhepa was a powerful Hittite queen and priestess known for her political influence, diplomatic correspondence, and role in international treaties during the 13th century BCE.
- 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_69eed2e14af88190bc70b4d0f3453aac |
completed | April 27, 2026, 3:07 a.m. |
Created at: April 16, 2026, 6:29 p.m.