Triple
T11376892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morena Baccarin |
E269491
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Firefly |
E313069
|
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: Firefly | Statement: [Morena Baccarin, appearedIn, Firefly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Firefly Context triple: [Morena Baccarin, appearedIn, Firefly]
-
A.
Firefly
chosen
Firefly is a cult-favorite science fiction television series created by Joss Whedon that blends space opera with Western themes and follows the ragtag crew of the spaceship Serenity.
-
B.
Firefly
Firefly is a Malaysian regional airline known for operating short-haul flights, often using turboprop aircraft to connect secondary cities and communities.
-
C.
Firefly
Firefly was a streamlined passenger train operated by the St. Louis–San Francisco Railway that provided fast, stylish service in the mid-20th century American Midwest.
-
D.
Firefly
Firefly is a DC Comics supervillain and pyromaniac arsonist known for using advanced incendiary weapons and a flight suit to terrorize Gotham City, often as an enemy of Batman.
-
E.
Firefly
Firefly is an Amazon-developed visual and audio recognition feature that lets users quickly identify products, media, and other real-world items using a smartphone camera or microphone.
- 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_69d6aacca1048190b39dbbc2174616fa |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea8e6d44819095f949581421e98e |
completed | April 9, 2026, 6:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e58bff6574819089bd63266b97a734 |
completed | April 20, 2026, 2:14 a.m. |
Created at: April 8, 2026, 9:33 p.m.