Triple
T32930006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Negeri Sembilan monarchy |
E842375
|
entity |
| Predicate | selectionBodyCollectiveName |
P1519
|
FINISHED |
| Object | Undang Yang Empat |
—
|
NE NERFINISHED |
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: Undang Yang Empat | Statement: [Negeri Sembilan monarchy, selectionBodyCollectiveName, Undang Yang Empat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: selectionBodyCollectiveName Context triple: [Negeri Sembilan monarchy, selectionBodyCollectiveName, Undang Yang Empat]
-
A.
usedCollectiveName
chosen
Indicates that a group of entities is referred to by a shared collective name.
-
B.
collectiveNameForm
Indicates that one entity serves as the collective or group name form used to refer to multiple members of another entity or class.
-
C.
collectivelyKnownAs
Indicates that multiple entities are referred to together under a single shared name or designation.
-
D.
groupOrDuoName
Indicates that the entities share a common name as a group or duo, identifying them collectively rather than individually.
-
E.
hasCollectiveCharacter
Indicates that a group or set of entities is treated as a unified whole, sharing a collective nature or identity rather than being considered solely as separate individuals.
- 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_69f34948adfc8190a937f1f622783c0b |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d26f27dc8190ae426a3e1573933e |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:20 a.m.