Triple
T19203817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NGC 5408 |
E480178
|
entity |
| Predicate | hasXRaySourceType |
P109994
|
FINISHED |
| Object | ultraluminous X-ray source |
—
|
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: ultraluminous X-ray source | Statement: [NGC 5408, hasXRaySourceType, ultraluminous X-ray source]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasXRaySourceType Context triple: [NGC 5408, hasXRaySourceType, ultraluminous X-ray source]
-
A.
hasXRaySources
Indicates that an entity possesses or is associated with one or more X-ray emitting sources.
-
B.
hasTypeOfSource
chosen
Indicates that one entity is classified as a particular kind or category of source in relation to another entity.
-
C.
hasPrimarySourceType
Indicates that something is associated with a main or original type of source from which information or evidence is directly obtained.
-
D.
hasRaySystem
Indicates that an entity possesses a radial arrangement or system of rays extending from a central point.
-
E.
hasMainSource
Indicates that one entity serves as the primary or principal source or origin for another entity.
- 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5f99b37c081908c13e0b4cca52aa4 |
completed | April 20, 2026, 10:02 a.m. |
| PD | Predicate disambiguation | batch_69e4dcf22b3c8190bee02e3af946e114 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:16 p.m.