Triple
T8393264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stefan Nemanja |
E197992
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Ras |
E316060
|
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: Ras | Statement: [Stefan Nemanja, capital, Ras]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ras Context triple: [Stefan Nemanja, capital, Ras]
-
A.
Ras
Ras is a high-ranking Ethiopian noble title historically bestowed upon powerful regional rulers and military leaders, roughly equivalent to a duke or prince.
-
B.
Ras
chosen
Ras is a historic medieval region and former capital area of the early Serbian state, known for its significant monasteries and fortifications.
-
C.
RasGas
RasGas was a major Qatari liquefied natural gas (LNG) company responsible for developing and operating some of Qatar’s largest gas projects.
-
D.
Ras Baraka
Ras Baraka is an American politician, educator, and poet who serves as the progressive mayor of Newark, New Jersey.
-
E.
Rasual
Rasual is the given name of Rasual Butler, an American professional basketball player who competed in the NBA.
- 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_69ca82f816bc8190ab321c07d72208c1 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb8184788081909e9857afff629985 |
completed | March 31, 2026, 8:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce02d5e0648190b33011c2ddca4ad3 |
completed | April 2, 2026, 5:47 a.m. |
Created at: March 30, 2026, 6:03 p.m.