Triple
T19626229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hannah Quinlivan |
E471141
|
entity |
| Predicate | appearedInFilm |
P795
|
FINISHED |
| Object | Skyfire |
—
|
NE NERFINISHED |
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: Skyfire | Statement: [Hannah Quinlivan, appearedInFilm, Skyfire]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skyfire Context triple: [Hannah Quinlivan, appearedInFilm, Skyfire]
-
A.
Skyfire
chosen
Skyfire is a 2019 Chinese disaster action film about a volcanic eruption at a luxury island resort, starring Hannah Quinlivan and directed by Simon West.
-
B.
Skywarp
Skywarp is a Decepticon Transformer best known as a teleporting Seeker jet and one of Megatron’s more mischievous and impulsive warriors.
-
C.
Skyper
Skyper is a prominent high-rise office and residential complex in Frankfurt am Main, Germany, known for its distinctive modern glass architecture.
-
D.
Kestrelflyer
Kestrelflyer is the frequent-flyer loyalty program of Air Mauritius, offering rewards and benefits to regular passengers of the airline.
-
E.
Jetfire
Jetfire is a heroic Autobot warrior in the Transformers franchise, often depicted as a powerful spacecraft and trusted second-in-command to Optimus Prime.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e511f28481909f4bc3ea9191e54a |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e9ff208190afb33c910ed2147b |
completed | April 20, 2026, 3:06 p.m. |
Created at: April 10, 2026, 1:44 p.m.