Triple
T20138383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aksi |
E491090
|
entity |
| Predicate | hasNearbyIsland |
P970
|
FINISHED |
| Object | Rammu |
—
|
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: Rammu | Statement: [Aksi, hasNearbyIsland, Rammu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rammu Context triple: [Aksi, hasNearbyIsland, Rammu]
-
A.
Rammu
chosen
Rammu is a small Estonian island in the Gulf of Finland, known for its natural landscapes and sparse habitation.
-
B.
Rahkshi
Rahkshi are iconic villainous biomechanical creatures from the Lego Bionicle universe, known for their fearsome armor, staff weapons, and role as powerful antagonists serving the dark lord Makuta.
-
C.
Shinzon
Shinzon is a human clone of Captain Jean-Luc Picard who leads a coup against the Romulan government and serves as the primary villain in the film Star Trek: Nemesis.
-
D.
Togarmah
Togarmah is a biblical figure mentioned in the Hebrew Bible as a descendant of Gomer and traditionally associated with peoples or regions in Anatolia or the Caucasus.
-
E.
Zagara
Zagara is a prominent Zerg broodmother and military commander in the StarCraft universe, known for leading the Swarm in Kerrigan’s absence.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667698a188190869c18b925dba2ed |
completed | April 20, 2026, 5:50 p.m. |
Created at: April 11, 2026, 11:32 p.m.