Triple
T4171998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TikTok |
E84583
|
entity |
| Predicate | hasAlgorithmName |
P54503
|
FINISHED |
| Object | For You recommendation algorithm |
—
|
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: For You recommendation algorithm | Statement: [TikTok, hasAlgorithmName, For You recommendation algorithm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlgorithmName Context triple: [TikTok, hasAlgorithmName, For You recommendation algorithm]
-
A.
hasAlgorithmNamedAfter
Indicates that an entity has an algorithm that is named after another entity.
-
B.
hasCodeName
Indicates that an entity is known or referred to by a particular alternative name or alias, often used for secrecy or distinction.
-
C.
hasNameFunction
Indicates that an entity is associated with a function whose purpose is to provide or determine its name.
-
D.
algorithmType
Indicates the specific kind or category of algorithm associated with an entity or process.
-
E.
usesEncryptionAlgorithm
Indicates that one entity applies or relies on a specific encryption algorithm to protect data or communications.
- 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_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. |
| PDg | Predicate description generation | batch_69af01ee94ec8190aa6dde54d4571c04 |
completed | March 9, 2026, 5:22 p.m. |
Created at: March 9, 2026, 3:45 p.m.