Triple
T4172043
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Instagram Reels |
E84584
|
entity |
| Predicate | primaryDiscoverySurface |
P44647
|
FINISHED |
| Object | Reels tab |
—
|
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: Reels tab | Statement: [Instagram Reels, primaryDiscoverySurface, Reels tab]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryDiscoverySurface Context triple: [Instagram Reels, primaryDiscoverySurface, Reels tab]
-
A.
primaryInterface
Indicates that one entity serves as the main or default interface through which another entity is accessed or interacted with.
-
B.
primaryView
chosen
Indicates that one view or representation is designated as the main or default perspective among multiple possible views of the same entity or content.
-
C.
primarySettingFeature
Indicates that a particular feature is the main or defining characteristic of a setting.
-
D.
primaryService
Indicates that one entity serves as the main or principal service provided or used in relation to another entity.
-
E.
discovery
Indicates the event or process by which one entity finds, uncovers, or identifies something previously unknown or unrecognized.
- F. None of above.
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_69aed932cab48190b80ffe35f7029ae1 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02c9e12c81908d0b22671fea2453 |
completed | March 9, 2026, 5:26 p.m. |
| PD | Predicate disambiguation | batch_69af018fb0948190a9701b2e8e5d9bac |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:45 p.m.