Triple
T3285947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Harbour |
E68980
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Netflix (for Stranger Things) |
E3004
|
NE 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: Netflix (for Stranger Things) | Statement: [David Harbour, employer, Netflix (for Stranger Things)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Netflix (for Stranger Things) Context triple: [David Harbour, employer, Netflix (for Stranger Things)]
-
A.
Netflix
Netflix is a global streaming entertainment company best known for its vast library of films and TV series and its influential original content.
-
B.
Netflix, Inc.
chosen
Netflix, Inc. is a leading global streaming entertainment company known for its vast library of films and TV series, including a significant slate of original content.
-
C.
Hulu
Hulu is a U.S.-based subscription streaming service offering on-demand access to a wide range of television shows, films, and original content.
-
D.
HBO Max
HBO Max is a streaming service from WarnerMedia that offers a wide library of movies, series, and original content from HBO and related brands.
-
E.
Tubi
Tubi is a free, ad-supported streaming service offering a large library of movies and TV shows on demand.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad859c463481909ca4be267336c290 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb03918c48190987d7cfd3bda9716 |
completed | March 8, 2026, 5:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e85b6a1081908581b2040b8ce261 |
completed | March 12, 2026, 4:22 p.m. |
Created at: March 8, 2026, 3:10 p.m.