Triple
T14078013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sky |
E338790
|
entity |
| Predicate | worksAt |
P7
|
FINISHED |
| Object | Donna’s taverna |
E908947
|
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: Donna’s taverna | Statement: [Sky, worksAt, Donna’s taverna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donna’s taverna Context triple: [Sky, worksAt, Donna’s taverna]
-
A.
Donna’s taverna
chosen
Donna’s taverna is the picturesque seaside Greek island bar and guesthouse that serves as the central setting of the musical and film "Mamma Mia!".
-
B.
Frank's Place
Frank's Place is an American television dramedy series from the late 1980s, acclaimed for its sophisticated storytelling and portrayal of life in New Orleans.
-
C.
Neir's Tavern
Neir's Tavern is a historic neighborhood bar in Woodhaven, Queens, often cited as one of New York City's oldest continuously operating taverns.
-
D.
Cookhouse
Cookhouse is a small rural town in South Africa’s Eastern Cape, known historically as a farming and railway junction settlement.
-
E.
Stowaway Tavern
Stowaway Tavern is a bar or pub-style establishment, likely a casual neighborhood spot known for drinks, socializing, and a laid-back atmosphere.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5e027881908f610f5bab7598d4 |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb670f51c819088e8d0137f8d3bb1 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.