Triple
T23244548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Net (畢宿, Bì Xiù) |
E581547
|
entity |
| Predicate | hasNumberInMansionsSequence |
P37553
|
FINISHED |
| Object | one of the western mansions |
—
|
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 of the western mansions | Statement: [Net (畢宿, Bì Xiù), hasNumberInMansionsSequence, one of the western mansions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNumberInMansionsSequence Context triple: [Net (畢宿, Bì Xiù), hasNumberInMansionsSequence, one of the western mansions]
-
A.
numberOfMansions
Indicates the quantity of mansions associated with a given entity.
-
B.
isNumberedBy
chosen
Indicates that an entity is assigned, identified, or organized by a specific number or numbering scheme.
-
C.
hasNumberOfHouses
Indicates the quantity of houses associated with a given entity.
-
D.
hasFictionalHouseNumberRange
Indicates that an entity is associated with a range of house numbers that are fictional or not used in real-world addressing.
-
E.
magicNumber
Indicates that an entity is a special constant or value with a particular, often hidden or predefined, significance within a system or context.
- 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193ee37c8819091f799506fa532da |
completed | April 29, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:10 p.m.