Triple
T29494405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress Wu (Gaozong) |
E748176
|
entity |
| Predicate | courtAffiliation |
P169682
|
FINISHED |
| Object | Song imperial harem |
—
|
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: Song imperial harem | Statement: [Empress Wu (Gaozong), courtAffiliation, Song imperial harem]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtAffiliation Context triple: [Empress Wu (Gaozong), courtAffiliation, Song imperial harem]
-
A.
courtName
Indicates the official name assigned to a particular court within a legal or judicial system.
-
B.
defendantAffiliation
Indicates that a defendant is formally associated or connected with a particular organization, group, or entity.
-
C.
courtCode
Indicates the specific court or judicial body associated with a legal case, proceeding, or record.
-
D.
courtFaction
Indicates a relationship where an entity is aligned with, belongs to, or is associated with a particular political or social faction within a court or ruling body.
-
E.
judicialCircuit
Indicates the judicial circuit within which a legal entity, case, or jurisdiction is organized or falls under authority.
- 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_69f0bd448c6881908aa6b475cefd5ddc |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f68048391c8190abe6580678f8a9ef |
completed | May 2, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
| PDg | Predicate description generation | batch_69f67f7e116c819099aec724e9ef3763 |
completed | May 2, 2026, 10:49 p.m. |
Created at: April 28, 2026, 4:17 p.m.