Triple
T21285567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cresphontes |
E524648
|
entity |
| Predicate | ethnicity |
P194
|
FINISHED |
| Object | Dorian |
—
|
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: Dorian | Statement: [Cresphontes, ethnicity, Dorian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dorian Context triple: [Cresphontes, ethnicity, Dorian]
-
A.
Dorian
chosen
Dorian is an ancient Greek ethnic and cultural identity traditionally associated with the Dorian Greeks, one of the major Hellenic tribes.
-
B.
Dorian
Dorian is the name of a powerful and destructive Atlantic hurricane whose severity led to its permanent retirement from the rotating list of storm names.
-
C.
Dorian
Dorian is a highly advanced, emotionally aware android police officer from the science fiction TV series "Almost Human."
-
D.
Dorian Tyrell
Dorian Tyrell is the main villain in the 1994 film "The Mask," a ruthless mobster who becomes even more dangerous after using the magical mask’s powers.
-
E.
DORIAN
DORIAN was the codename for the high-resolution reconnaissance camera system developed for the U.S. Air Force’s Manned Orbiting Laboratory program during the Cold War.
- 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_69e0b5171f6c8190a5d57201ede73811 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736d658e08190ad2f267123d53ede |
completed | April 21, 2026, 8:35 a.m. |
Created at: April 16, 2026, 4:03 p.m.