Triple
T5350512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas's leaf monkey |
E124165
|
entity |
| Predicate | groupComposition |
P11600
|
FINISHED |
| Object | one-male multi-female groups |
—
|
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: one-male multi-female groups | Statement: [Thomas's leaf monkey, groupComposition, one-male multi-female groups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: groupComposition Context triple: [Thomas's leaf monkey, groupComposition, one-male multi-female groups]
-
A.
partyComposition
chosen
Indicates how the members or elements of a group or party are arranged, distributed, or combined to form that party as a whole.
-
B.
personnelComposition
Indicates the makeup or distribution of people or roles within a group, organization, or unit.
-
C.
peopleGroupWithin
Indicates that one group of people is geographically or organizationally contained within another group of people.
-
D.
groups
Indicates that one entity organizes, clusters, or associates multiple entities together as members of a collective set or category.
-
E.
participantGroup
Indicates a relationship in which a set or group of entities jointly participate in a common event, activity, or interaction.
- 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_69bd464be27081908807b40b75c1bbae |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd860fe4048190846a933d0e1b9386 |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.