Triple
T1634429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Docs |
E35329
|
entity |
| Predicate | supportsRealTimePresence |
P30775
|
FINISHED |
| Object | cursor indicators for collaborators |
—
|
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: cursor indicators for collaborators | Statement: [Google Docs, supportsRealTimePresence, cursor indicators for collaborators]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsRealTimePresence Context triple: [Google Docs, supportsRealTimePresence, cursor indicators for collaborators]
-
A.
globalPresence
Indicates that an entity operates, is represented, or has a significant footprint across multiple countries or world regions.
-
B.
onlinePresence
Indicates that an entity maintains a presence or representation on the internet, such as through websites, profiles, or digital platforms.
-
C.
mediaPresence
Indicates the extent to which something is visible, represented, or covered within various media channels or platforms.
-
D.
hasHumanPresence
Indicates that humans are physically present in or occupying a given location, object, or context.
-
E.
supportsMultiRoomAudio
Indicates that the subject is capable of playing synchronized audio across multiple rooms or speakers simultaneously.
- 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_69a886036bc081909ff5de16dbe5e8ea |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a96083e7308190abbf025fe8e43abb |
completed | March 5, 2026, 10:52 a.m. |
| PD | Predicate disambiguation | batch_69a907cac610819083cafd4396b6d66c |
completed | March 5, 2026, 4:34 a.m. |
| PDg | Predicate description generation | batch_69a9607716b4819092187f8c08daaf31 |
completed | March 5, 2026, 10:52 a.m. |
Created at: March 4, 2026, 7:28 p.m.