Triple
T11867951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Museum of Taiwan History |
E282331
|
entity |
| Predicate | offersEducationalProgram |
P69363
|
FINISHED |
| Object | guided tours |
—
|
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: guided tours | Statement: [National Museum of Taiwan History, offersEducationalProgram, guided tours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersEducationalProgram Context triple: [National Museum of Taiwan History, offersEducationalProgram, guided tours]
-
A.
offersEducationIn
Indicates that an entity provides or delivers educational programs, courses, or instruction in a specified field, subject, or area.
-
B.
offersEducationTo
Indicates that one entity provides educational services, instruction, or learning opportunities to another entity.
-
C.
offersProfessionalPrograms
Indicates that an entity provides formal, career-oriented educational or training programs to others.
-
D.
hasEducationalProgram
Indicates that an entity offers, runs, or is associated with a specific educational program.
-
E.
programOffered
chosen
Indicates that a particular program is made available or provided by a given entity (such as an institution, organization, or provider).
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a73c04e4819084c0b2ff8e5d2f04 |
completed | April 10, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69d8a2589f0c8190ad82ff11acabae93 |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.