Triple
T32855897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haochen Zhang |
E840372
|
entity |
| Predicate | performanceActivity |
P178585
|
FINISHED |
| Object | gives concerts internationally |
—
|
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: gives concerts internationally | Statement: [Haochen Zhang, performanceActivity, gives concerts internationally]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performanceActivity Context triple: [Haochen Zhang, performanceActivity, gives concerts internationally]
-
A.
performanceWith
Indicates a relationship where two or more entities participate together in the same performance or staged presentation.
-
B.
performanceArea
Indicates the area or space in which a performance, show, or event takes place.
-
C.
performanceEvent
chosen
Indicates that an event involves a live or recorded artistic, musical, theatrical, or similar performance taking place.
-
D.
performanceAs
Indicates that one entity serves in a particular role, character, or capacity within a performance or presentation involving another entity.
-
E.
performanceOutcome
Indicates the result, effect, or consequence produced by a particular performance or action.
- 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_69f349412c78819084459850e11d29f7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fe349879848190bcd77e3cc3470458 |
completed | May 8, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_69fe31e3cf908190b23ebc2f7fe58722 |
completed | May 8, 2026, 6:56 p.m. |
Created at: May 1, 2026, 1:17 a.m.