Triple
T9093356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pippa Middleton |
E217947
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Philippa |
E278786
|
NE 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: Philippa | Statement: [Pippa Middleton, givenName, Philippa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Philippa Context triple: [Pippa Middleton, givenName, Philippa]
-
A.
Philippa
chosen
Philippa was a medieval European queen consort, most famously Philippa of Hainault, wife of King Edward III of England.
-
B.
Euphemia
Euphemia was the wife of Byzantine Emperor Justin I and served as empress consort of the Eastern Roman Empire in the early 6th century.
-
C.
Timothea
Timothea is a feminine given name derived from the name Timothy, often interpreted to mean "honoring God."
-
D.
Tiphaine
Tiphaine is a French given name, notably borne by Tiphaine Auzière, the daughter of Brigitte Macron.
-
E.
Sheelagh
Sheelagh is a feminine given name, typically considered an alternative spelling of Sheila and ultimately derived from the Irish name Síle.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca83d8ab5881909d8fddae363b32b1 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc96b347d4819085b33d0e20834f47 |
completed | April 1, 2026, 3:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d01803b0288190a86b544892d4b6ed |
completed | April 3, 2026, 7:41 p.m. |
Created at: March 30, 2026, 7:14 p.m.