Triple
T33547778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanjong Katong Girls' School |
E859251
|
entity |
| Predicate | schoolUniformColor |
P3502
|
FINISHED |
| Object | green |
—
|
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: green | Statement: [Tanjong Katong Girls' School, schoolUniformColor, green]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: schoolUniformColor Context triple: [Tanjong Katong Girls' School, schoolUniformColor, green]
-
A.
hasSchoolUniform
Indicates that an entity is required to wear or is associated with a specific school uniform as part of its affiliation with a school.
-
B.
hasSchoolColours
Indicates that an entity is associated with one or more official colours that represent it, typically in formal or symbolic contexts.
-
C.
wearsUniformColor
Indicates that an entity regularly uses or is associated with a specific uniform color as part of its standard attire or dress code.
-
D.
hasHomeUniformTrimColor
Indicates that an entity’s home uniform features a specified trim or accent color.
-
E.
homeUniformColorPrimary
chosen
Indicates the primary color used for an entity’s home uniform in a given context.
- 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_69f3497a5be08190a39b12736899e034 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f96badb08190994442c2aba840b1 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:39 a.m.