Triple
T5432810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TVMLKit |
E121535
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object |
TVJS
TVJS is a JavaScript framework used for building interactive tvOS applications, often in conjunction with TVMLKit for Apple TV user interfaces.
|
E518837
|
NE FINISHED |
How this triple was built (4 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: TVJS | Statement: [TVMLKit, relatedTo, TVJS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TVJS Context triple: [TVMLKit, relatedTo, TVJS]
-
A.
VIDN
VIDN is the four-letter ICAO airport code assigned to Noida International Airport in Uttar Pradesh, India.
-
B.
KTCM
KTCM is the ICAO airport code for McChord Field, the U.S. Air Force installation that forms part of Joint Base Lewis–McChord in Washington State.
-
C.
Watch TCM app
The Watch TCM app is a streaming platform that lets users watch Turner Classic Movies’ curated library of classic films and related content on demand.
-
D.
SVT Play
SVT Play is Sweden’s national public service broadcaster’s online streaming platform, offering on-demand and live TV content.
-
E.
Vdio
Vdio was an online video-on-demand and streaming service launched by Skype and Rdio co-founder Janus Friis as an attempt to compete with platforms like Netflix.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: TVJS Triple: [TVMLKit, relatedTo, TVJS]
Generated description
TVJS is a JavaScript framework used for building interactive tvOS applications, often in conjunction with TVMLKit for Apple TV user interfaces.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: TVJS Target entity description: TVJS is a JavaScript framework used for building interactive tvOS applications, often in conjunction with TVMLKit for Apple TV user interfaces.
-
A.
VIDN
VIDN is the four-letter ICAO airport code assigned to Noida International Airport in Uttar Pradesh, India.
-
B.
KTCM
KTCM is the ICAO airport code for McChord Field, the U.S. Air Force installation that forms part of Joint Base Lewis–McChord in Washington State.
-
C.
Watch TCM app
The Watch TCM app is a streaming platform that lets users watch Turner Classic Movies’ curated library of classic films and related content on demand.
-
D.
SVT Play
SVT Play is Sweden’s national public service broadcaster’s online streaming platform, offering on-demand and live TV content.
-
E.
Vdio
Vdio was an online video-on-demand and streaming service launched by Skype and Rdio co-founder Janus Friis as an attempt to compete with platforms like Netflix.
- F. None of above. chosen
Provenance (5 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_69bd463c65f0819082ee6483ab4b466a |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd8840ade481909dae2eecc77d73b8 |
completed | March 20, 2026, 5:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf3ac985e48190ba9610e0563c73ab |
completed | March 22, 2026, 12:41 a.m. |
| NEDg | Description generation | batch_69bf3b663b148190807d35421c911d74 |
completed | March 22, 2026, 12:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf3c2b9d04819081a946e9f68c4eb2 |
completed | March 22, 2026, 12:47 a.m. |
Created at: March 20, 2026, 2:06 p.m.