Triple
T3075247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steel Curtain defense of the 1970s |
E64119
|
entity |
| Predicate | anchorUnit |
P12481
|
FINISHED |
| Object | defensive line |
—
|
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: defensive line | Statement: [Steel Curtain defense of the 1970s, anchorUnit, defensive line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: anchorUnit Context triple: [Steel Curtain defense of the 1970s, anchorUnit, defensive line]
-
A.
associatedUnitType
Indicates that one entity is linked to or characterized by a particular type or category of unit.
-
B.
basedUnit
Indicates that one unit is defined in terms of, or derived from, another more fundamental unit.
-
C.
associatedWithUnit
chosen
Indicates that one entity has a connection, linkage, or affiliation with a particular unit (such as a division, department, or organizational subunit).
-
D.
principalUnitUntil
Indicates that one entity serves as the primary or principal unit for another entity up to, but not beyond, a specified point in time.
-
E.
anchorTenant
Indicates that an entity serves as a primary or major tenant whose presence helps attract other tenants or users to a shared space or platform.
- 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_69ad857a8aec8190bfdfd9c14554ac5a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada150d8e08190bde5f68e800e8feb |
completed | March 8, 2026, 4:18 p.m. |
| PD | Predicate disambiguation | batch_69ad9625b30c819099ef9349c91d7b25 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:02 p.m.