Triple
T17012801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalie Mendoza |
E412741
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Descent |
E200832
|
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: The Descent | Statement: [Natalie Mendoza, notableWork, The Descent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Descent Context triple: [Natalie Mendoza, notableWork, The Descent]
-
A.
The Descent
chosen
The Descent is a 2005 British horror film about a group of women who become trapped and hunted by creatures in an uncharted cave system.
-
B.
Into the Abyss
Into the Abyss is a 2011 documentary film by Werner Herzog that explores a Texas triple homicide case and the human realities surrounding capital punishment.
-
C.
Deep Rising
Deep Rising is a 1998 action-horror film about mercenaries who encounter a deadly sea creature aboard a luxury cruise ship.
-
D.
The Dark Descent
The Dark Descent is a highly regarded horror fiction anthology edited by David G. Hartwell that showcases a wide-ranging survey of classic and modern dark fantasy and horror stories.
-
E.
Underdark
The Underdark is a vast, perilous subterranean realm of caverns, tunnels, and strange civilizations beneath the surface world in the Dungeons & Dragons setting.
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d47dab688190bf486bcf0b40ed4f |
completed | April 18, 2026, 6:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b4990948190861ff81f8fc3e8f2 |
completed | May 10, 2026, 11:56 p.m. |
Created at: April 10, 2026, 5:33 a.m.