Triple
T32059554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boy (2010 film) |
E818709
|
entity |
| Predicate | countryBoxOfficeRecord |
P172230
|
FINISHED |
| Object | highest-grossing New Zealand film at its 2010 release |
—
|
LITERAL 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: highest-grossing New Zealand film at its 2010 release | Statement: [Boy (2010 film), countryBoxOfficeRecord, highest-grossing New Zealand film at its 2010 release]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryBoxOfficeRecord Context triple: [Boy (2010 film), countryBoxOfficeRecord, highest-grossing New Zealand film at its 2010 release]
-
A.
countryBoxOfficeGrossUSD
Indicates the total box office revenue, in U.S. dollars, that a work earned within a specific country.
-
B.
boxOfficeWorldwideINR
Indicates the total worldwide box office revenue of a work, expressed in Indian Rupees (INR).
-
C.
boxOfficeTerritoryLabel
chosen
Indicates the specific geographic territory or market associated with a box office performance or revenue figure.
-
D.
boxOfficeInternationalUSD
Indicates the amount of money a work earned in international (non-domestic) box offices, measured in U.S. dollars.
-
E.
boxOfficeGrossUSD
Indicates the total amount of money an entity earned at the box office, expressed in U.S. dollars.
- F. None of above.
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_69f348fdacec8190b9f74375ca3b2094 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a002ae74da08190a4b47e0ff0f7f8fe |
completed | May 10, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_6a0029cc369c81909578e52c4a75ab18 |
completed | May 10, 2026, 6:46 a.m. |
Created at: May 1, 2026, 12:21 a.m.