Triple
T37142845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maglor’s Gap |
E920161
|
entity |
| Predicate | defendedDuring |
P190100
|
FINISHED |
| Object | Siege of Angband |
—
|
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: Siege of Angband | Statement: [Maglor’s Gap, defendedDuring, Siege of Angband]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defendedDuring Context triple: [Maglor’s Gap, defendedDuring, Siege of Angband]
-
A.
defendedOn
Indicates that one entity protected, supported, or argued in favor of another entity during a specific time or event.
-
B.
alsoDefendedOn
Indicates that an entity was additionally defended on another specified date or occasion, beyond its primary defense time.
-
C.
alsoDefendedIn
Indicates that the same entity or case was defended in an additional context, such as another court, proceeding, or jurisdiction.
-
D.
defendedAtEvent
Indicates that an entity (typically a work, thesis, or position) was formally defended or argued for during a specific event.
-
E.
defendedAs
Indicates that one entity is presented, argued, or justified as being equivalent to or serving the role of another entity in a defensive or protective context.
- F. None of above. chosen
Provenance (4 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_69f76e9e9d008190a250b0387c992c74 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
| PDg | Predicate description generation | batch_69fcab6d41a88190a3576b4b088dcabd |
completed | May 7, 2026, 3:10 p.m. |
Created at: May 3, 2026, 4:15 p.m.