Triple
T24337519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Draco (river) |
E613419
|
entity |
| Predicate | sourceCountryModern |
P13520
|
FINISHED |
| Object | Lebanon |
—
|
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: Lebanon | Statement: [Draco (river), sourceCountryModern, Lebanon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceCountryModern Context triple: [Draco (river), sourceCountryModern, Lebanon]
-
A.
homeCountryModern
Indicates that one entity is the modern-day country that serves as the home or origin country of the other entity.
-
B.
modernCountryContains
chosen
Indicates that a modern country geographically encompasses, within its current internationally recognized borders, the location or territory of another entity.
-
C.
modernCountryClaim
Indicates that a modern country asserts sovereignty, ownership, or official association with a given entity or territory.
-
D.
laterCountryOfOrigin
Indicates that an entity’s country of origin changed, and this predicate specifies the country that became its origin at a later time than a previously associated country.
-
E.
historicalOriginCountry
Indicates the country from which something originally came or first emerged in a historical context.
- F. None of above.
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_69e2d7dcc5a08190b53691130d56cbc4 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f293212a0881908da028e81d26247d |
completed | April 29, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_69f287ad30048190b3ad3613486f277f |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:57 a.m.