Triple
T313079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Balanchine |
E7646
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Apollo |
E12942
|
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: Apollo | Statement: [George Balanchine, notableWork, Apollo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Apollo Context triple: [George Balanchine, notableWork, Apollo]
-
A.
Apollo
chosen
Apollo is the Olympian god of the sun, music, prophecy, and healing in ancient Greek mythology.
-
B.
Artemis
Artemis is the Greek goddess of the hunt, wilderness, and childbirth, often depicted as a virgin huntress and protector of young women and animals.
-
C.
Hyperion
Hyperion is a romantic travelogue novel by Henry Wadsworth Longfellow that blends fiction, philosophy, and lyrical descriptions of Germany.
-
D.
Hyperion
Hyperion is one of Saturn’s larger, irregularly shaped moons, known for its chaotic rotation and sponge-like, heavily cratered surface.
-
E.
Orion
Orion is a prominent constellation in the night sky, easily recognized by its three-star belt and associated in many cultures with the figure of a hunter.
- 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_69a2e7e7af7881908890039d6be4e9b8 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ea4bd6a081909bdb57602c7093b4 |
completed | Feb. 28, 2026, 1:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3bc2963b48190b5bd7ac84c952486 |
completed | March 1, 2026, 4:10 a.m. |
Created at: Feb. 28, 2026, 1:07 p.m.