Triple
T10880552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karen Gillan |
E256907
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Oculus |
E730770
|
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: Oculus | Statement: [Karen Gillan, notableWork, Oculus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oculus Context triple: [Karen Gillan, notableWork, Oculus]
-
A.
Oculus
The Oculus is a striking, winged transportation hub and shopping center in Lower Manhattan designed by architect Santiago Calatrava, serving as the main transit hall for the rebuilt World Trade Center site.
-
B.
Oculus
chosen
Oculus is a 2013 psychological horror film written and directed by Mike Flanagan that centers on a haunted mirror and the traumatic effects it has on a family.
-
C.
Oculus VR
Oculus VR is a virtual reality technology company best known for developing the Oculus Rift headset and helping popularize modern consumer VR experiences.
-
D.
Oculus Rift
Oculus Rift is a virtual reality headset developed by Oculus VR that enables immersive 3D gaming and interactive experiences on PC.
-
E.
Oculus Go
Oculus Go is a standalone virtual reality headset designed for untethered, mobile VR experiences without the need for a PC or smartphone.
- 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_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d751b031a88190b1182dfc1f520264 |
completed | April 9, 2026, 7:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dff7e2322c8190a55605237ae6ce95 |
completed | April 15, 2026, 8:41 p.m. |
Created at: April 8, 2026, 9:21 p.m.