Triple
T23205545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Muhammad ibn Tughj al-Ikhshid |
E580442
|
entity |
| Predicate | maintainedNominalLoyaltyTo |
P94124
|
FINISHED |
| Object | Abbasid caliph |
—
|
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: Abbasid caliph | Statement: [Muhammad ibn Tughj al-Ikhshid, maintainedNominalLoyaltyTo, Abbasid caliph]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintainedNominalLoyaltyTo Context triple: [Muhammad ibn Tughj al-Ikhshid, maintainedNominalLoyaltyTo, Abbasid caliph]
-
A.
isLoyalTo
chosen
Indicates that one entity consistently supports, respects, or remains faithful to another entity.
-
B.
formerLoyalty
Indicates that an entity previously had a loyalty or allegiance to another entity, but no longer does.
-
C.
loyaltyDimension
Indicates the degree or aspect of loyalty characterizing the relationship between entities.
-
D.
loyaltyAlliance
Indicates a committed, supportive alliance in which one party maintains steadfast loyalty to another.
-
E.
loyaltySymbolizedBy
Indicates that an instance of loyalty is represented or expressed by a particular symbol or emblem.
- 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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1907c1d7c8190aca252a39ae0da86 |
completed | April 29, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69effcccee508190a7ae311fdd319806 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:07 p.m.