Triple
T37104898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IC 4617 |
E918814
|
entity |
| Predicate | positionRelativeToM13 |
P201046
|
FINISHED |
| Object | very close in the same telescopic field |
—
|
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: very close in the same telescopic field | Statement: [IC 4617, positionRelativeToM13, very close in the same telescopic field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionRelativeToM13 Context triple: [IC 4617, positionRelativeToM13, very close in the same telescopic field]
-
A.
positionRelativeToHod
Indicates the spatial or positional relationship of an entity with respect to a specified hod (a particular reference point or unit in a structured space).
-
B.
positionRelativeToSurface
Indicates how an entity is spatially located or oriented with respect to a reference surface.
-
C.
trackPositionOnHomogenic
Indicates that an entity’s position is monitored or recorded along a uniform, consistent medium or coordinate space.
-
D.
relativePositionInSystem
Indicates the spatial or ordered position an entity occupies within a larger system or structured arrangement.
-
E.
positionRelativeToBMP
Indicates that one entity’s spatial position is defined relative to a specified reference point or frame called the BMP.
- 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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffc3f0b19c8190b5a749bc3cad21dd |
completed | May 9, 2026, 11:32 p.m. |
| PD | Predicate disambiguation | batch_69ffc1b882808190932b2d43ea5537c9 |
completed | May 9, 2026, 11:22 p.m. |
| PDg | Predicate description generation | batch_69ffc3eed97c819085c06ffe3699ff38 |
completed | May 9, 2026, 11:31 p.m. |
Created at: May 3, 2026, 4:14 p.m.