Triple
T215895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Australia Day |
E4103
|
entity |
| Predicate | alsoCalledByCritics |
P9702
|
FINISHED |
| Object | Survival Day |
E27453
|
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: Survival Day | Statement: [Australia Day, alsoCalledByCritics, Survival Day]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Survival Day Context triple: [Australia Day, alsoCalledByCritics, Survival Day]
-
A.
Invasion Day
chosen
Invasion Day is a term used by critics of Australia Day to highlight and protest the colonization of Australia and its ongoing impacts on Indigenous peoples.
-
B.
Save the Night
"Save the Night" is a song by John Legend from his R&B album "Love in the Future."
-
C.
Day of Goodwill
Day of Goodwill is a South African public holiday observed on December 26 that focuses on charity, generosity, and spending time with family and community.
-
D.
Savior
Savior is a Christian title for Jesus Christ, emphasizing his role as the divine redeemer who delivers humanity from sin and spiritual death.
-
E.
The Brave One
The Brave One is a 2007 psychological thriller film in which Jodie Foster plays a New York radio host who becomes a vigilante after a brutal attack.
- 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_69a2573508588190b522c2476d91acfe |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a260c3037c8190ba7ddf328f249b74 |
completed | Feb. 28, 2026, 3:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a34d935eb48190a6f327ae77917d2c |
completed | Feb. 28, 2026, 8:18 p.m. |
Created at: Feb. 28, 2026, 2:53 a.m.