Triple
T37214673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sack of Nargothrond |
E922705
|
entity |
| Predicate | destroyedPlace |
P53686
|
FINISHED |
| Object | Nargothrond |
—
|
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: Nargothrond | Statement: [Sack of Nargothrond, destroyedPlace, Nargothrond]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: destroyedPlace Context triple: [Sack of Nargothrond, destroyedPlace, Nargothrond]
-
A.
landmarksDestroyed
Indicates that certain notable or significant physical landmarks have been damaged or completely destroyed.
-
B.
palaceDemolished
Indicates that a palace has been destroyed or torn down, typically as a completed event.
-
C.
destroyedCity
Indicates that an entity has caused the complete or near-complete destruction of a city.
-
D.
demolishedOrDestroyed
Indicates that one entity has caused another entity to be torn down, ruined, or rendered unusable, typically through deliberate demolition or destructive force.
-
E.
locationOfDestruction
chosen
Indicates the place where a destruction event occurred or where something was destroyed.
- F. None of above.
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_69f76ea6f5288190b8d9988f613811c0 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:15 p.m.