Triple
T4584386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donovan |
E101932
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Atlantis |
E118802
|
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: Atlantis | Statement: [Donovan, notableWork, Atlantis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Atlantis Context triple: [Donovan, notableWork, Atlantis]
-
A.
Atlantis
chosen
Atlantis is a legendary, highly advanced island civilization from ancient Greek mythology, said to have sunk into the sea as a result of divine punishment.
-
B.
Atlantis
Atlantis is a retired NASA Space Shuttle orbiter that flew numerous missions for the United States space program between 1985 and 2011.
-
C.
Journey to Atlantis
Journey to Atlantis is a water coaster attraction that combines roller coaster thrills with themed dark-ride elements inspired by the mythological lost city of Atlantis.
-
D.
Atlantis: The Lost Empire
Atlantis: The Lost Empire is a 2001 Disney animated science-fiction adventure film that follows a linguist and a diverse expedition team on a journey to discover the lost underwater city of Atlantis.
-
E.
Atlantis Appendix
Atlantis Appendix is a renowned 17th-century cartographic work by Dutch mapmaker Willem Blaeu, notable for its detailed maps and contributions to early modern atlas publishing.
- 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_69bd43d4ce208190b53158c882b222e3 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd590411dc81909c55d1c42a4d44ef |
completed | March 20, 2026, 2:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bde0a18c90819083953e78fc6de8db |
completed | March 21, 2026, 12:04 a.m. |
Created at: March 20, 2026, 1:10 p.m.