Triple
T36404645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stadium Merdeka |
E896717
|
entity |
| Predicate | countryAtOpening |
P878
|
FINISHED |
| Object | Federation of Malaya |
E36705
|
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: Federation of Malaya | Statement: [Stadium Merdeka, countryAtOpening, Federation of Malaya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryAtOpening Context triple: [Stadium Merdeka, countryAtOpening, Federation of Malaya]
-
A.
openingCountry
Indicates the country in which something (such as a business, event, or production) is first opened, launched, or premiered.
-
B.
formerCountryAtOpening
Indicates that an entity was previously recognized as a country at the time another entity (such as an event, organization, or facility) was established or opened.
-
C.
countryStart
Indicates that an entity marks the beginning or starting point of a country-related extent, boundary, or association.
-
D.
countryOn
Indicates that one country is located on or occupies the territory of another geographic entity (such as a larger region, continent, or island).
-
E.
countryAtTheTime
chosen
Indicates that an entity is associated with a specific country as it existed at a particular point in time.
- F. None of above.
Provenance (4 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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a030713bd2881908bcc69e7d1e9fd09 |
completed | May 12, 2026, 10:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39dbbe30cc819081d6b7d9a4103c43 |
completed | June 23, 2026, 1:05 a.m. |
| PD | Predicate disambiguation | batch_6a0304c29abc819085ffd17ab9a8c844 |
completed | May 12, 2026, 10:45 a.m. |
Created at: May 3, 2026, 4:10 p.m.