Triple
T9115997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sack of Erebor |
E218719
|
entity |
| Predicate | notableSurvivor |
P2116
|
FINISHED |
| Object | Ori |
E778873
|
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: Ori | Statement: [Sack of Erebor, notableSurvivor, Ori]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ori Context triple: [Sack of Erebor, notableSurvivor, Ori]
-
A.
Ori
Ori is the official three-letter IAU abbreviation for the constellation Orion, one of the most recognizable star patterns in the night sky.
-
B.
Ori
chosen
Ori is a young, scholarly dwarf from J.R.R. Tolkien’s legendarium, best known as one of Thorin Oakenshield’s companions on the quest to reclaim Erebor in The Hobbit.
-
C.
Ori series
The Ori series is a critically acclaimed set of atmospheric, story-driven platform-adventure games known for their hand-painted art, emotional storytelling, and challenging precision platforming.
-
D.
Akurio
The Akurio are a small Indigenous people of the Guianas, traditionally semi-nomadic hunter-gatherers living in the rainforest regions of Suriname.
-
E.
Taitō
Taitō is a special ward in central Tokyo known for its historic districts, traditional temples, and major cultural attractions such as Ueno Park and Asakusa.
- 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_69ca83dc94ac8190b9ef42684d36ff39 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8a4c9e08190ba3603a5d00afb20 |
completed | April 1, 2026, 5:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d047baf5e48190aab0eb19908fabfc |
completed | April 3, 2026, 11:05 p.m. |
Created at: March 30, 2026, 7:16 p.m.