Triple
T36548056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Utumno |
E901185
|
entity |
| Predicate | relationToAngband |
P204929
|
FINISHED |
| Object | primary stronghold before Angband |
—
|
LITERAL 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: primary stronghold before Angband | Statement: [Utumno, relationToAngband, primary stronghold before Angband]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationToAngband Context triple: [Utumno, relationToAngband, primary stronghold before Angband]
-
A.
relationToMid-World
Indicates a relationship in which something is connected or relevant to a central or intermediate world, realm, or domain.
-
B.
relationshipToCharacter
Indicates the specific type of personal, social, or narrative connection that one entity has to a given character.
-
C.
relationshipToRelative
Indicates the specific familial connection or kinship role that one person has in relation to a particular relative.
-
D.
relationshipToHumans
Indicates the nature or type of connection, association, or relevance that something has specifically with humans.
-
E.
relationToAncestors
Indicates a familial relationship that connects an entity to one or more of its ancestors in a lineage or hierarchy.
- 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_69f76e61217081908b79d610fe67b013 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82f8c88190bd77a086023ac0e1 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:11 p.m.