Triple
T11613696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tilley |
E275447
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Tilly |
E505451
|
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: Tilly | Statement: [Tilley, hasVariant, Tilly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tilly Context triple: [Tilley, hasVariant, Tilly]
-
A.
Tilly
chosen
Tilly is the commonly used name for Johann Tserclaes, Count of Tilly, a prominent general of the Catholic League during the early stages of the Thirty Years' War.
-
B.
Tilly
Tilly is one of the short stories included in James Joyce’s collection *Pomes Penyeach*.
-
C.
Lillete
Lillete is an alcoholic beverage brand that forms part of Pernod Ricard’s global spirits and drinks portfolio.
-
D.
Tilley
Tilley is an English surname of Norman origin that has been borne by various notable figures, including early American colonists.
-
E.
Hallie
Hallie is a friendly, talking hippo nurse character who assists Doc McStuffins in caring for toys in the animated children's television series.
- 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_69d6aaf84b548190ac072e4fb89ae18f |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a044a3088190b92f4674c2d0b443 |
completed | April 10, 2026, 7:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e8a84161d88190a3e810d19d6ea8b8 |
completed | April 22, 2026, 10:51 a.m. |
Created at: April 8, 2026, 9:38 p.m.