Triple
T5094085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hrothgar |
E114823
|
entity |
| Predicate | workLocation |
P7
|
FINISHED |
| Object | Heorot |
E493752
|
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: Heorot | Statement: [Hrothgar, workLocation, Heorot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heorot Context triple: [Hrothgar, workLocation, Heorot]
-
A.
Heorot
chosen
Heorot is the great mead hall in the Old English epic Beowulf, famed as King Hrothgar’s royal hall and the site of Grendel’s attacks.
-
B.
Halldon
Halldon is a fictional continent on the planet Skaro in the Doctor Who universe, known as part of the Daleks’ homeworld geography.
-
C.
Håkons Hall
Håkons Hall is a large multi-purpose indoor arena in Lillehammer, Norway, best known for hosting ice hockey events during the 1994 Winter Olympics.
-
D.
Throne Hall
The Throne Hall is a grand ceremonial chamber within Gatchina Palace, historically used for imperial receptions and official court functions.
-
E.
Loevestein Castle
Loevestein Castle is a medieval Dutch fortress in the Netherlands, best known as a state prison and the site of Hugo Grotius’s famous escape in a book chest.
- 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_69bd443fc49c819089629c00e311310c |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75454920819086e09d6055087e40 |
completed | March 20, 2026, 4:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bed912629c8190beffde376f0aedc7 |
completed | March 21, 2026, 5:44 p.m. |
Created at: March 20, 2026, 1:40 p.m.