Triple
T36546118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gates of Sirion |
E901143
|
entity |
| Predicate | guardedAgainst |
P101950
|
FINISHED |
| Object |
forces of Morgoth
The forces of Morgoth were the vast and fearsome armies of the first Dark Lord in J.R.R. Tolkien’s legendarium, composed of Orcs, Balrogs, dragons, and other corrupted beings waging war against the Free Peoples of Middle-earth.
|
E2188871
|
NE FINISHED |
How this triple was built (3 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: forces of Morgoth | Statement: [Gates of Sirion, guardedAgainst, forces of Morgoth]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: forces of Morgoth Triple: [Gates of Sirion, guardedAgainst, forces of Morgoth]
Generated description
The forces of Morgoth were the vast and fearsome armies of the first Dark Lord in J.R.R. Tolkien’s legendarium, composed of Orcs, Balrogs, dragons, and other corrupted beings waging war against the Free Peoples of Middle-earth.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardedAgainst Context triple: [Gates of Sirion, guardedAgainst, forces of Morgoth]
-
A.
guardedIn
Indicates that one entity is protected or kept under watch within the bounds or premises of another entity.
-
B.
guardedAs
Indicates that one entity is protected, watched over, or kept secure in the role or capacity specified by another entity.
-
C.
securedAgainst
chosen
Indicates that one entity is protected or safeguarded against threats, risks, or harmful actions originating from another entity or source.
-
D.
protectedBy
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
E.
protectedFor
Indicates that something is safeguarded or preserved specifically for the benefit, use, or rights of a particular entity or purpose.
- F. None of above.
Provenance (6 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_69f7cec454a88190a9f3bbee2b856636 |
completed | May 3, 2026, 10:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39e6e7f008819084e79eb4c57c7b3b |
completed | June 23, 2026, 1:52 a.m. |
| NEDg | Description generation | batch_6a39eac8d58c8190a3460d838efd2cf8 |
completed | June 23, 2026, 2:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a39ec59cb748190b664869d96b2b868 |
completed | June 23, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f7c8977c288190997a892ec5f756ed |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:11 p.m.