Triple
T25533600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SteamVR |
E639987
|
entity |
| Predicate | supportsTrackingSystem |
P180839
|
FINISHED |
| Object | Lighthouse tracking |
—
|
LITERAL 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: Lighthouse tracking | Statement: [SteamVR, supportsTrackingSystem, Lighthouse tracking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsTrackingSystem Context triple: [SteamVR, supportsTrackingSystem, Lighthouse tracking]
-
A.
trackSystem
Indicates a relationship where one entity monitors, records, or follows the status, behavior, or changes of another entity within a system.
-
B.
supportsWorldSystem
Indicates that one entity upholds, maintains, or enables the functioning or stability of a particular world system or global framework.
-
C.
usesTrackage
Indicates that one transportation operator or service runs its vehicles over railway or transit tracks that are owned or controlled by another entity.
-
D.
hasTrackFacility
Indicates that one entity provides or includes a track facility (such as a running or racing track) available for use by another entity.
-
E.
trackingAvailable
Indicates that tracking information or functionality is available for the associated item, process, or interaction.
- F. None of above. chosen
Provenance (4 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_69e75dbf3f9c8190b3f2a75d1b75d127 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
| PDg | Predicate description generation | batch_69f75788d40c819083bf2567b3091585 |
completed | May 3, 2026, 2:11 p.m. |
Created at: April 21, 2026, 3:16 p.m.