Triple
T20889661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Priam's house |
E514374
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | city of Troy |
—
|
NE NERFINISHED |
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: city of Troy | Statement: [Priam's house, partOf, city of Troy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: city of Troy Context triple: [Priam's house, partOf, city of Troy]
-
A.
city of Troy
The city of Troy is an upstate New York city on the eastern bank of the Hudson River, historically known for its industrial heritage and as part of the Capital District near Albany.
-
B.
ancient Troy
chosen
Ancient Troy was a legendary Bronze Age city in northwestern Anatolia, famed as the setting of the Trojan War in Greek mythology and the focus of extensive archaeological excavations.
-
C.
Troia
Troia is a historic town in Italy’s Apulia region, known for its medieval architecture and Romanesque cathedral.
-
D.
Tróia
Tróia is a Portuguese peninsula and resort area known for its long sandy beaches, Roman ruins, and proximity to the city of Setúbal.
-
E.
Τροῖα
Τροῖα is the legendary ancient city in northwestern Asia Minor that was besieged by the Greeks in the Trojan War, as recounted in Homeric epic.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d05d591481908c9c999db76760fc |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 12:46 p.m.