Triple
T38550389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | γ Herculis |
E925093
|
entity |
| Predicate | multipleSystemComponents |
P191185
|
FINISHED |
| Object | at least two |
—
|
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: at least two | Statement: [γ Herculis, multipleSystemComponents, at least two]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: multipleSystemComponents Context triple: [γ Herculis, multipleSystemComponents, at least two]
-
A.
multipleWorkingSystem
Indicates that an entity is associated with or operates within more than one working system simultaneously.
-
B.
isPrimaryComponentOfMultipleSystem
Indicates that an entity serves as the main or central component in more than one distinct system.
-
C.
modelsSystemsWith
Indicates that one entity creates or uses a representation or abstraction to describe, analyze, or simulate another system.
-
D.
systemUsedBy
Indicates that a particular system is utilized or operated by a specified agent or user.
-
E.
associatedSystem
Indicates that one entity is functionally or contextually linked to a particular system with which it interacts or to which it belongs.
- F. None of above. chosen
Provenance (4 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_69f76eaeb69c8190b367df9330d6f6af |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
| PDg | Predicate description generation | batch_69fcdaa2bfc08190beccabb0f1782d0d |
completed | May 7, 2026, 6:32 p.m. |
Created at: May 3, 2026, 4:32 p.m.