Triple
T19020720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laomedon |
E465476
|
entity |
| Predicate | grandparent |
P2400
|
FINISHED |
| Object | Tros |
—
|
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: Tros | Statement: [Laomedon, grandparent, Tros]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tros Context triple: [Laomedon, grandparent, Tros]
-
A.
Tros
chosen
Tros is a figure in Greek mythology known as the eponymous founder and king of Troy, from whom the Trojans derive their name.
-
B.
Trogen
Trogen is a municipality in the canton of Appenzell Ausserrhoden in northeastern Switzerland, known for its picturesque setting and traditional Swiss architecture.
-
C.
Dardanos
Dardanos was an ancient town in the Troad region of northwestern Anatolia, known from Greek and Roman sources and associated with early Trojan legends.
-
D.
Troy
Troy is a historic city in eastern New York State, known for its 19th-century architecture and role in the Industrial Revolution as a major manufacturing center.
-
E.
Troy
Troy is a 2004 epic historical war film loosely based on Homer's Iliad, depicting the legendary conflict between the Greeks and Trojans.
- 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_69d8dd025c188190a1d81f5b4ec7e2c6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6de93408190a98dea2319f1af62 |
completed | April 20, 2026, 7:33 a.m. |
Created at: April 10, 2026, 12:02 p.m.